Benchmark scores for recent small open-weight AI models.
Generated 2026-10-12T17:42:24Z
Listed by release date, newest first. Click any column header to sort (Params / Benchmarks / AA-Index sort numerically, Released by date; click again to flip direction; missing values sink to the bottom). A V badge marks models that support vision / multimodal (image) input.
| Model | Family | Params | Architecture | License | Released | Benchmarks | AA-Index-v4.3 |
|---|---|---|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3BV | MiniCPM-V-4.7-35B-A3B | 35.2B | moe | Apache 2.0 | 2026-10-07 | 33 | — |
| Agnes-3.0-FlashV | Agnes-3.0-Flash | 33.1B | dense | Apache 2.0 | 2026-09-11 | 6 | 36 |
| Nex-N2.5-miniV | Nex-N2.5 | 35.1B | moe | Apache 2.0 | 2026-09-08 | 16 | — |
| MiniCPM5-2B | MiniCPM5-2B | 2.5B | dense | Apache 2.0 | 2026-09-06 | 34 | 14 |
| Ling-3.0-flash-VLV | Ling-3.0-flash-VL | 124.8B | moe | MIT | 2026-09-04 | 13 | 25 |
| K2-Horizon-MoVA-36B-A4B | K2-Horizon-MoVA-36B-A4B | 37.4B | moe | Apache 2.0 | 2026-09-01 | 10 | 26 |
| K2-Horizon-7B | K2-Horizon-7B | 9B | dense | Apache 2.0 | 2026-09-01 | 9 | 21 |
| K2-Horizon-3.7B | K2-Horizon-3.7B | 5.1B | dense | Apache 2.0 | 2026-09-01 | 9 | 16 |
| Qwen3.8-Flash-NextV | Qwen3.8 | 180B | moe | other | 2026-08-24 | 23 | 42 |
| Spark-X2.5-4B | Spark X | 4.1B | dense | Apache 2.0 | 2026-08-24 | 21 | — |
| Ornith-1.5-9BV | Ornith | 9.7B | dense | MIT | 2026-08-18 | 13 | — |
| Ornith-1.5-35B-A3BV | Ornith | 36B | moe | MIT | 2026-08-18 | 15 | — |
| Ling-3.0-tiny | Ling | 7.9B | moe | MIT | 2026-08-10 | 18 | 12 |
| Muse-Glimmer-30BV | Muse-Glimmer-30B | 29.8B | dense | Apache 2.0 | 2026-08-09 | 28 | 18 |
| granite-4.2-30b | granite-4.2 | 29.3B | dense | Apache 2.0 | 2026-08-07 | 20 | 15 |
| granite-4.2-8b | granite-4.2 | 8.8B | dense | Apache 2.0 | 2026-08-07 | 20 | 12 |
| Qwen3.8-27BV | Qwen3.8 | 27.8B | dense | Apache 2.0 | 2026-08-05 | 26 | 34 |
| Ling-3.0-flash | Ling | 127.5B | moe | MIT | 2026-08-02 | 26 | 25 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | Nemotron-3.5 | 31.6B | moe | other | 2026-08-01 | 15 | 14 |
| LongCat-Flash-Lite-Sparse | LongCat | 69.1B | dense | MIT | 2026-07-31 | 30 | 11 |
| KAT-Coder-V2.5-DevV | KAT-Coder | 34.7B | dense | Apache 2.0 | 2026-07-23 | 7 | — |
| Nanbeige4.2-3B | Nanbeige4.2 | 4.2B | dense | Apache 2.0 | 2026-07-21 | 21 | — |
| Laguna-S-2.1 | Laguna | 117.6B | moe | openmdw-1.1 | 2026-07-13 | 6 | — |
| DeepSeek-V4-Flash-DSpark | DeepSeek-V4 | 165.3B | moe | MIT | 2026-06-27 | 22 | 35 |
| Qwen-AgentWorld-35B-A3BV | Qwen-AgentWorld | 34.7B | moe | Apache 2.0 | 2026-06-22 | 1 | — |
| Laguna-XS-2.1 | Laguna | 33.4B | moe | openmdw-1.1 | 2026-06-20 | 4 | — |
| diffusiongemma-26B-A4B-itV | diffusiongemma | 25.8B | moe | Apache 2.0 | 2026-06-09 | 15 | 10 |
| North-Mini-Code-1.0 | North | 30.5B | moe | Apache 2.0 | 2026-06-05 | 10 | 13 |
| LFM2.5-8B-A1B | LFM2.5 | 8.5B | moe | other | 2026-05-28 | 13 | 7 |
| gemma-4-12B-itV | gemma-4 | 12B | dense | Apache 2.0 | 2026-05-23 | 17 | 14 |
| Hy-MT2-30B-A3B | Hy-MT2 | 30.1B | moe | Apache 2.0 | 2026-05-11 | 9 | — |
| Nemotron-3-Nano-Omni-30B-A3B-ReasoningV | Nemotron-3 | 33B | moe | other | 2026-04-20 | 12 | 10 |
Cell shows the score for that model×benchmark; grey = absent / no numeric score. Cell colour is scaled per benchmark (light → deep blue = lower → higher); the gold cell is the best model on that benchmark. Columns are ordered by how many models report each benchmark. Click a benchmark column to rank models by it; click the Model column to sort by name.
| Model | Terminal-Bench 2.1 | Terminal-Bench 2.0 | Terminal-Bench Hard | AA-Intelligence-… | GPQA Diamond | HLE | SWE-bench Pro | IFBench | SWE-bench Verifi… | SciCode | AIME 2026 | AIME 2025 | SWE-bench Multil… | LiveCodeBench v6 | LiveCodeBench | LiveCodeBench 2408-2505 | AA-LCR | HMMT Feb 2026 | HMMT Feb 2025 | τ³-bench | BFCL v4 | BFCL v3 | BrowseComp | MMLU-Pro | MCP-Atlas | τ²-bench | CharXiv | IMO AnswerBench | MathVision | DeepSWE 1.1 | DeepSWE | MMMU Pro | MRCR | MRCR v2 | OmniDocBench 1.5 | GDPval-AA-V2 | IFEval | Multi-IF | NL2Repo-Bench | Toolathlon | Vision2Web | AA-Omniscience A… | ClawEval | ClawEval-MM | Codeforces ELO | GDPval | GDPval-AA | JobBench | MATH500 | OSWorld-Verified | WideSearch | Agents' Last Exa… | AndroidWorld | Arena-Hard-V2 | ArtifactsBench | BigBench Extra H… | BirdBench | BrowseComp-zh | CMMLU | Claw-Gym | CoWorkBench | ERQA | LIFEbench | LongBench-v2 | MMLU-ProX lite | MMMLU | MedXPertQA MM | OCRBench 2 | OSWorld | PinchBench | ProfBench | RULER | RealWorldQA | RecreationBench | SWE Atlas | SWE-MM | SkillsBench | SuperGPQA | Toolathlon-Verif… | VideoMME | WebArena-Verifie… |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8-27BV | 73 | · | · | 34 | 89.2 | 30.8 | 61.7 | 79.5 | · | · | · | · | · | 90.3 | · | · | · | · | · | · | · | · | · | · | · | · | 90.2 | · | 94.6 | 42.2 | · | · | · | · | 91.1 | · | · | · | 42.3 | · | 62.9 | · | · | 57.4 | · | · | · | 33.4 | · | 84.3 | · | 42.9 | 81.9 | · | · | · | · | · | · | · | 70.7 | 65.5 | · | · | · | · | · | · | · | · | · | · | 85.9 | 47.1 | · | 38.6 | · | · | · | · | 64.8 |
| Qwen3.8-Flash-NextVMoE | · | · | · | 42 | 91.7 | 35.9 | 62.5 | 81.3 | · | · | · | · | 81 | 91.9 | · | · | · | · | · | · | · | · | · | · | · | · | 90.6 | · | 95.7 | 58.7 | · | · | · | · | · | · | · | · | 48.1 | 73.5 | 64 | · | · | 64.4 | · | · | · | 55.7 | · | · | · | 51.2 | 84.5 | · | · | · | · | · | · | · | 73.9 | 72.3 | · | · | · | · | · | · | 52.3 | · | · | · | 88.5 | 49.9 | · | · | · | · | · | · | · |
| Qwen-AgentWorld-35B-A3BVMoE | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| gemma-4-12B-itV | · | · | · | 14 | 78.8 | 5.2 | · | · | · | · | 77.5 | · | · | 72 | · | · | · | · | · | · | · | · | · | 77.2 | · | 69 | · | · | 79.7 | · | · | 69.1 | · | 43.4 | 0.2 | · | · | · | · | · | · | · | · | · | 1659 | · | · | · | · | · | · | · | · | · | · | 53 | · | · | · | · | · | · | · | · | · | 83.4 | 48.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| diffusiongemma-26B-A4B-itVMoE | · | · | · | 10 | 73.2 | 11.9 | · | · | · | · | 69.1 | · | · | 69.1 | · | · | · | · | · | · | · | · | · | 77.6 | · | 56.2 | · | · | 70.5 | · | · | 54.3 | · | 32 | 0.3 | · | · | · | · | · | · | · | · | · | 1429 | · | · | · | · | · | · | · | · | · | · | 47.6 | · | · | · | · | · | · | · | · | · | 81.5 | 49 | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| DeepSeek-V4-Flash-DSparkMoE | · | 56.9 | · | 35 | 88.1 | 45.1 | 52.6 | · | 79 | · | · | · | 73.3 | · | 91.6 | · | · | 94.8 | · | · | · | · | 73.2 | 86.2 | 69 | · | · | 88.4 | · | · | · | · | 78.7 | · | · | · | · | · | · | 47.8 | · | · | · | · | 3052 | · | 1395 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| Laguna-S-2.1MoE | 70.2 | · | · | · | · | · | 59.4 | · | · | · | · | · | 78.5 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 40.4 | · | · | · | · | · | · | · | · | 49.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 46.2 | · | · | · | · | · | · |
| Laguna-XS-2.1MoE | · | 37.5 | · | · | · | · | 47.6 | · | 70.9 | · | · | · | 63.1 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| LFM2.5-8B-A1BMoE | · | · | · | 7 | · | · | · | 56.5 | · | · | 50 | 42.5 | · | · | · | · | · | · | · | · | 49.7 | 64.8 | · | · | · | 88.1 | · | · | · | · | · | · | · | · | · | · | 91.8 | 79.9 | · | · | · | 8.7 | · | · | · | · | · | · | 88.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| Nanbeige4.2-3B | · | 44.1 | · | · | 87.4 | 17.8 | 46.9 | 54.6 | 63.6 | 35.6 | · | · | · | 72.5 | · | · | 58.7 | 82.8 | · | · | · | · | · | · | 57.8 | · | · | 67.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 52.2 | · | · | 74.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | 65 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| KAT-Coder-V2.5-DevV | 41.0 | · | · | · | · | · | 46.0 | · | 69.4 | 44.2 | · | · | 63 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 93.4 | · | · | · | · | · | · | · | · | · | · | · |
| North-Mini-Code-1.0MoE | · | 36 | 31.1 | 13 | 75.7 | 11.1 | 40.2 | 57.5 | 67.6 | 38.2 | · | · | · | 70.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| granite-4.2-30b | 29.2 | · | · | 15 | 66.4 | · | 33.3 | 77.2 | 57 | 38.8 | · | 89.2 | 41.9 | 75.8 | · | · | · | · | 89.2 | 62 | 61.4 | · | · | 77.6 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 1225 | · | · | · | · | · | · | · | 67.9 | · | · | 41.9 | · | · | · | · | · | · | · | 66.6 | · | · | · | · | · | 42.9 | 90.0 | · | · | · | · | · | · | · | · | · |
| granite-4.2-8b | 20.6 | · | · | 12 | 64.1 | · | 19.1 | 79.3 | 47.7 | 36.1 | · | 86.7 | 30.8 | 73.2 | · | · | · | · | 78.3 | 58.1 | 52.4 | · | · | 74.0 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 1189 | · | · | · | · | · | · | · | 65.2 | · | · | 41.1 | · | · | · | · | · | · | · | 61.1 | · | · | · | · | · | 41.2 | 81.0 | · | · | · | · | · | · | · | · | · |
| Hy-MT2-30B-A3BMoE | · | · | · | · | · | · | · | 50.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 89.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| LongCat-Flash-Lite-Sparse | · | 33.7 | · | 11 | 69.5 | · | 40.6 | · | 68.2 | · | 65.7 | · | 59.3 | · | · | · | 48 | 41.5 | · | · | · | · | 48.6 | 79.2 | 45.6 | 96.0 | · | 49.4 | · | · | · | · | 44.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 96.8 | · | · | · | · | · | · | · | · | 61.9 | 84.5 | · | · | · | · | 53.6 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| Nemotron-3-Nano-Omni-30B-A3B-ReasoningVMoE | · | · | · | 10 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 63.6 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 67.0 | 47.4 | · | · | · | · | · | · | · | · | · | · | 72.2 | · |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16MoE | 24.6 | · | · | 14 | 75.4 | 11.7 | · | 71.9 | 51.6 | 32.6 | · | · | 39.3 | · | · | · | 52 | · | · | 9.3 | · | · | 37.0 | 81.9 | · | · | · | · | · | · | · | · | · | · | · | 832 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 85.4 | · | · | · | · | · | · | · | · | · | · | · |
| Ornith-1.5-9BV | 47 | · | · | · | 86.4 | 30.5 | 47.5 | · | 70.6 | · | · | · | 54.4 | · | · | · | · | · | · | · | · | · | 56.4 | · | 54.2 | · | · | · | · | · | · | · | · | · | · | · | · | · | 32.4 | · | · | · | 66.5 | · | · | · | · | · | · | · | 59.5 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 41.2 | · | · |
| Ornith-1.5-35B-A3BVMoE | 68.5 | · | · | · | 89.2 | 33.4 | 59.6 | · | 79 | · | · | · | 71.4 | · | · | · | · | · | · | · | · | · | 67.6 | · | 70.2 | · | · | · | · | · | 22 | · | · | · | · | · | · | · | 46.2 | 48.7 | · | · | 72.5 | · | · | · | · | · | · | · | 67.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 39.8 | · | · | · | · | · | · |
| Ling-3.0-tinyMoE | 27.7 | · | · | 12 | 73.4 | 9.3 | · | 63.6 | · | 24.2 | · | · | · | · | · | · | 58.7 | 70.3 | · | 20.8 | 62.7 | · | · | · | · | · | · | 71.0 | · | · | · | · | · | · | · | · | · | 83.2 | · | · | · | · | · | · | · | · | 772 | · | · | · | · | · | · | · | 47.9 | · | · | · | · | · | · | · | 62.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| Ling-3.0-flashMoE | 57 | · | · | 25 | · | 22.7 | 56.6 | 74.5 | · | · | 93.2 | · | 72.4 | · | · | 82.8 | 65.1 | 87 | · | 28 | 73 | · | 82 | · | 65.5 | · | · | 83.7 | · | · | · | · | 90.8 | · | · | · | · | 87.7 | · | · | · | · | · | · | · | · | 1107 | · | · | · | 73.6 | · | · | · | 77 | · | · | · | · | · | · | · | 77.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | 44.8 | · | · | · | · |
| Spark-X2.5-4B | · | · | · | · | 67.4 | 12.3 | 44.4 | 75 | 41.6 | 34.7 | 90.7 | · | 53.3 | · | · | · | 56.3 | 81.2 | · | 30.4 | 65.1 | · | 40.9 | · | 54.6 | 75.1 | · | 74.2 | · | · | · | · | · | · | · | · | 93 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| K2-Horizon-MoVA-36B-A4BMoE | 58.6 | · | · | 26 | 80.8 | 25.2 | · | · | · | 38.9 | · | · | · | · | · | · | 66.3 | · | · | 26.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 18.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| K2-Horizon-7B | 39.1 | · | · | 21 | · | 18.6 | · | · | 70.6 | 31.6 | · | · | · | · | · | · | 68 | 73.3 | · | 25.8 | · | · | 59 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| MiniCPM5-2B | 8.6 | · | · | 14 | 70.2 | 8.9 | 14.4 | 66.3 | 46.4 | 26.3 | 86.5 | 86.5 | · | 69.1 | · | · | 59 | 63.8 | · | 20.8 | 66.6 | · | 39.7 | 70.8 | · | 97.1 | · | · | · | · | · | · | · | · | · | 19.6 | 86.7 | 71.8 | · | · | · | · | · | · | · | · | · | · | 94.6 | · | · | · | · | · | · | · | · | 43.5 | · | 59.2 | · | · | · | 43.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | 40.8 | · | · | · |
| Nex-N2.5-miniVMoE | 73.4 | · | · | · | · | · | 43.8 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 83.4 | · | · | · | · | · | · | 36.1 | · | · | · | · | · | 1446 | · | · | · | · | 52.9 | · | · | · | · | · | · | 28.5 | · | 71.2 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 25.5 | · | · | 54.6 | · | 63.4 |
| Ling-3.0-flash-VLVMoE | · | · | · | 25 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 81.3 | · | 84.9 | · | · | 79 | · | · | 91.3 | · | · | · | · | · | 57.7 | · | · | 59.9 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| Muse-Glimmer-30BV | 51.7 | · | · | 18 | 83.5 | 22 | 51.2 | 77 | 76 | 43.6 | 94.7 | · | · | · | · | · | 80 | · | · | 23.5 | · | · | · | · | 75.5 | · | 78.8 | · | · | · | · | 74 | · | · | 75.8 | 953 | · | · | · | · | · | · | · | · | · | · | · | · | · | 65.9 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 44.3 | · | · | · | · |
| Agnes-3.0-FlashV | · | · | · | 36 | 85.0 | · | · | 74.2 | · | 38.1 | · | · | · | · | · | · | 68.3 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 23 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| K2-Horizon-3.7B | 25.1 | · | · | 16 | 65.4 | 12.9 | · | · | 68.6 | 25.9 | · | · | · | · | · | · | · | 70.5 | · | 17.7 | 50.9 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · |
| MiniCPM-V-4.7-35B-A3BVMoE | · | · | · | · | · | · | · | 47.7 | · | · | 76.5 | · | · | 56.6 | · | · | · | · | · | · | 60.1 | · | · | 83.5 | · | 84.7 | 75.6 | · | 74.2 | · | · | 69.7 | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | · | 90.2 | · | · | · | · | · | · | · | · | 68.5 | · | · | · | · | · | · | · | · | · | 61.2 | · | 76.4 | · |
Bar charts compare the top 10 models (by score) that report the same benchmark (≥2 models within the parameter range above). Hover a bar for the exact value.
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Nex-N2.5-mini | 73.4 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 73 | % | Terminus | Hugging Face model card | link |
| Laguna-S-2.1 | 70.2 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 68.5 | % | Claude Code | Hugging Face model card | link |
| K2-Horizon-MoVA-36B-A4B | 58.6 | % | Hugging Face model card | link | |
| Ling-3.0-flash | 57 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 51.7 | % | with terminus2 | Hugging Face model card | link |
| Ornith-1.5-9B | 47 | % | Claude Code | Hugging Face model card | link |
| KAT-Coder-V2.5-Dev | 41.0 | % | avg of two harnesses | Hugging Face model card | link |
| K2-Horizon-7B | 39.1 | % | Hugging Face model card | link | |
| granite-4.2-30b | 29.2 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 27.7 | % | Hugging Face model card | link | |
| K2-Horizon-3.7B | 25.1 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 24.6 | % | Hugging Face model card | link | |
| granite-4.2-8b | 20.6 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 8.6 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 56.9 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 44.1 | % | Hugging Face model card | link | |
| Laguna-XS-2.1 | 37.5 | % | pass@1 (avg over 5 attempts) | Hugging Face model card | link |
| North-Mini-Code-1.0 | 36 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 33.7 | % | w/o HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| North-Mini-Code-1.0 | 31.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 42 | index | Artificial Analysis | link | |
| Agnes-3.0-Flash | 36 | points | Artificial Analysis | link | |
| DeepSeek-V4-Flash-DSpark | 35 | index | reasoning level: Reasoning, Max Effort (highest) | Artificial Analysis | link |
| Qwen3.8-27B | 34 | index | reasoning level: xhigh (highest) | Artificial Analysis | link |
| K2-Horizon-MoVA-36B-A4B | 26 | index | Artificial Analysis | link | |
| Ling-3.0-flash | 25 | index | Artificial Analysis | link | |
| Ling-3.0-flash-VL | 25 | index | Artificial Analysis | link | |
| K2-Horizon-7B | 21 | index | Artificial Analysis | link | |
| Muse-Glimmer-30B | 18 | index | reasoning level: high (highest) | Artificial Analysis | link |
| K2-Horizon-3.7B | 16 | index | Artificial Analysis | link | |
| granite-4.2-30b | 15 | index | Artificial Analysis | link | |
| gemma-4-12B-it | 14 | index | reasoning level: Reasoning (highest) | Artificial Analysis | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 14 | index | Artificial Analysis | link | |
| MiniCPM5-2B | 14 | index | Artificial Analysis | link | |
| North-Mini-Code-1.0 | 13 | index | Artificial Analysis | link | |
| granite-4.2-8b | 12 | index | Artificial Analysis | link | |
| Ling-3.0-tiny | 12 | index | Artificial Analysis | link | |
| LongCat-Flash-Lite-Sparse | 11 | index | Artificial Analysis | link | |
| diffusiongemma-26B-A4B-it | 10 | index | Artificial Analysis | link | |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 10 | index | Artificial Analysis | link | |
| LFM2.5-8B-A1B | 7 | index | Artificial Analysis | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 91.7 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 89.2 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 89.2 | % | Hugging Face model card | link | |
| DeepSeek-V4-Flash-DSpark | 88.1 | % | Pass@1 | Hugging Face model card | link |
| Nanbeige4.2-3B | 87.4 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 86.4 | % | Hugging Face model card | link | |
| Agnes-3.0-Flash | 85.0 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 83.5 | % | high reasoning | Hugging Face model card | link |
| K2-Horizon-MoVA-36B-A4B | 80.8 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 78.8 | % | Hugging Face model card | link | |
| North-Mini-Code-1.0 | 75.7 | % | Overall | Artificial Analysis | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 75.4 | % | no tools | Hugging Face model card | link |
| Ling-3.0-tiny | 73.4 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 73.2 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 70.2 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 69.5 | % | avg@16, w/o HI | Hugging Face model card | link |
| Spark-X2.5-4B | 67.4 | % | Hugging Face model card | link | |
| granite-4.2-30b | 66.4 | % | Hugging Face model card | link | |
| K2-Horizon-3.7B | 65.4 | % | Hugging Face model card | link | |
| granite-4.2-8b | 64.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 45.1 | % | with tools, Pass@1 | Hugging Face model card | link |
| Qwen3.8-Flash-Next | 35.9 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 33.4 | % | with tools | Hugging Face model card | link |
| Qwen3.8-27B | 30.8 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 30.5 | % | with tools | Hugging Face model card | link |
| K2-Horizon-MoVA-36B-A4B | 25.2 | % | no tools | Hugging Face model card | link |
| Ling-3.0-flash | 22.7 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 22 | % | high reasoning, text | Hugging Face model card | link |
| K2-Horizon-7B | 18.6 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 17.8 | % | w/o search | Hugging Face model card | link |
| K2-Horizon-3.7B | 12.9 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 12.3 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 11.9 | % | with search | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 11.7 | % | text-only, no tools | Hugging Face model card | link |
| North-Mini-Code-1.0 | 11.1 | % | Overall | Artificial Analysis | link |
| Ling-3.0-tiny | 9.3 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 8.9 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 5.2 | % | no tools | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 62.5 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 61.7 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 59.6 | % | Hugging Face model card | link | |
| Laguna-S-2.1 | 59.4 | % | Public Dataset | Hugging Face model card | link |
| Ling-3.0-flash | 56.6 | % | Hugging Face model card | link | |
| DeepSeek-V4-Flash-DSpark | 52.6 | % | Resolved | Hugging Face model card | link |
| Muse-Glimmer-30B | 51.2 | % | Hugging Face model card | link | |
| Laguna-XS-2.1 | 47.6 | % | Public Dataset, pass@1 (avg over 2 attempts) | Hugging Face model card | link |
| Ornith-1.5-9B | 47.5 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 46.9 | % | Hugging Face model card | link | |
| KAT-Coder-V2.5-Dev | 46.0 | % | pass@1 | Hugging Face model card | link |
| Spark-X2.5-4B | 44.4 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 43.8 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 40.6 | % | w/o HI | Hugging Face model card | link |
| North-Mini-Code-1.0 | 40.2 | % | Overall | Hugging Face model card | link |
| granite-4.2-30b | 33.3 | % | Hugging Face model card | link | |
| granite-4.2-8b | 19.1 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 14.4 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 81.3 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 79.5 | % | Hugging Face model card | link | |
| granite-4.2-8b | 79.3 | % | prompt | Hugging Face model card | link |
| granite-4.2-30b | 77.2 | % | prompt | Hugging Face model card | link |
| Muse-Glimmer-30B | 77 | % | high reasoning | Hugging Face model card | link |
| Spark-X2.5-4B | 75 | % | Hugging Face model card | link | |
| Ling-3.0-flash | 74.5 | % | Hugging Face model card | link | |
| Agnes-3.0-Flash | 74.2 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 71.9 | % | loose | Hugging Face model card | link |
| MiniCPM5-2B | 66.3 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 63.6 | % | Hugging Face model card | link | |
| North-Mini-Code-1.0 | 57.5 | % | Overall | Artificial Analysis | link |
| LFM2.5-8B-A1B | 56.5 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 54.6 | % | Hugging Face model card | link | |
| Hy-MT2-30B-A3B | 50.7 | % | Overall | Official tech report / arXiv paper | link |
| MiniCPM-V-4.7-35B-A3B | 47.7 | % | instruct | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 79 | % | Resolved | Hugging Face model card | link |
| Ornith-1.5-35B-A3B | 79 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 76 | % | Hugging Face model card | link | |
| Laguna-XS-2.1 | 70.9 | % | pass@1 (avg over 4 attempts) | Hugging Face model card | link |
| Ornith-1.5-9B | 70.6 | % | Hugging Face model card | link | |
| K2-Horizon-7B | 70.6 | % | Hugging Face model card | link | |
| KAT-Coder-V2.5-Dev | 69.4 | % | pass@1 | Hugging Face model card | link |
| K2-Horizon-3.7B | 68.6 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 68.2 | % | w/o HI | Hugging Face model card | link |
| North-Mini-Code-1.0 | 67.6 | % | Overall | Hugging Face model card | link |
| Nanbeige4.2-3B | 63.6 | % | Hugging Face model card | link | |
| granite-4.2-30b | 57 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 51.6 | % | Overall | Hugging Face model card | link |
| granite-4.2-8b | 47.7 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 46.4 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 41.6 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| KAT-Coder-V2.5-Dev | 44.2 | % | pass@1 | Hugging Face model card | link |
| Muse-Glimmer-30B | 43.6 | % | Hugging Face model card | link | |
| K2-Horizon-MoVA-36B-A4B | 38.9 | % | Overall | Hugging Face model card | link |
| granite-4.2-30b | 38.8 | % | Hugging Face model card | link | |
| North-Mini-Code-1.0 | 38.2 | % | Overall | Hugging Face model card | link |
| Agnes-3.0-Flash | 38.1 | % | Hugging Face model card | link | |
| granite-4.2-8b | 36.1 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 35.6 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 34.7 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 32.6 | % | Overall | Hugging Face model card | link |
| K2-Horizon-7B | 31.6 | % | Overall | Hugging Face model card | link |
| MiniCPM5-2B | 26.3 | % | Hugging Face model card | link | |
| K2-Horizon-3.7B | 25.9 | % | Overall | Hugging Face model card | link |
| Ling-3.0-tiny | 24.2 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Muse-Glimmer-30B | 94.7 | % | high reasoning | Hugging Face model card | link |
| Ling-3.0-flash | 93.2 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 90.7 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 86.5 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 77.5 | % | no tools | Hugging Face model card | link |
| MiniCPM-V-4.7-35B-A3B | 76.5 | % | avg@16, instruct | Hugging Face model card | link |
| diffusiongemma-26B-A4B-it | 69.1 | % | no tools | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 65.7 | % | avg@32, w/o HI | Hugging Face model card | link |
| LFM2.5-8B-A1B | 50 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 89.2 | % | Hugging Face model card | link | |
| granite-4.2-8b | 86.7 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 86.5 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 42.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 81 | % | Hugging Face model card | link | |
| Laguna-S-2.1 | 78.5 | % | Hugging Face model card | link | |
| DeepSeek-V4-Flash-DSpark | 73.3 | % | Resolved | Hugging Face model card | link |
| Ling-3.0-flash | 72.4 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 71.4 | % | Hugging Face model card | link | |
| Laguna-XS-2.1 | 63.1 | % | pass@1 (avg over 4 attempts) | Hugging Face model card | link |
| KAT-Coder-V2.5-Dev | 63 | % | pass@1 | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 59.3 | % | w/o HI | Hugging Face model card | link |
| Ornith-1.5-9B | 54.4 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 53.3 | % | Hugging Face model card | link | |
| granite-4.2-30b | 41.9 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 39.3 | % | Overall | Hugging Face model card | link |
| granite-4.2-8b | 30.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 91.9 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 90.3 | % | Hugging Face model card | link | |
| granite-4.2-30b | 75.8 | % | Hugging Face model card | link | |
| granite-4.2-8b | 73.2 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 72.5 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 72 | % | Hugging Face model card | link | |
| North-Mini-Code-1.0 | 70.3 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 69.1 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 69.1 | % | Hugging Face model card | link | |
| MiniCPM-V-4.7-35B-A3B | 56.6 | % | instruct | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 91.6 | % | Pass@1 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 82.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Muse-Glimmer-30B | 80 | % | Hugging Face model card | link | |
| Agnes-3.0-Flash | 68.3 | % | Hugging Face model card | link | |
| K2-Horizon-7B | 68 | % | Overall | Hugging Face model card | link |
| K2-Horizon-MoVA-36B-A4B | 66.3 | % | Overall | Hugging Face model card | link |
| Ling-3.0-flash | 65.1 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 59 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 58.7 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 58.7 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 56.3 | % | Hugging Face model card | link | |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 52 | idx | Overall | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 48 | % | w/o HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 94.8 | % | Pass@1 | Hugging Face model card | link |
| Ling-3.0-flash | 87 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 82.8 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 81.2 | % | Hugging Face model card | link | |
| K2-Horizon-7B | 73.3 | % | Hugging Face model card | link | |
| K2-Horizon-3.7B | 70.5 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 70.3 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 63.8 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 41.5 | % | avg@32, w/ HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 89.2 | % | Hugging Face model card | link | |
| granite-4.2-8b | 78.3 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 62 | % | avg | Hugging Face model card | link |
| granite-4.2-8b | 58.1 | % | avg | Hugging Face model card | link |
| Spark-X2.5-4B | 30.4 | % | Hugging Face model card | link | |
| Ling-3.0-flash | 28 | % | Banking | Hugging Face model card | link |
| K2-Horizon-MoVA-36B-A4B | 26.8 | % | Banking | Hugging Face model card | link |
| K2-Horizon-7B | 25.8 | % | Banking | Hugging Face model card | link |
| Muse-Glimmer-30B | 23.5 | % | Banking | Hugging Face model card | link |
| Ling-3.0-tiny | 20.8 | % | Banking | Hugging Face model card | link |
| MiniCPM5-2B | 20.8 | % | Banking | Hugging Face model card | link |
| K2-Horizon-3.7B | 17.7 | % | Banking | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 9.3 | % | Banking | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 73 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 66.6 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 65.1 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 62.7 | % | Hugging Face model card | link | |
| granite-4.2-30b | 61.4 | % | Hugging Face model card | link | |
| MiniCPM-V-4.7-35B-A3B | 60.1 | % | instruct | Hugging Face model card | link |
| granite-4.2-8b | 52.4 | % | Hugging Face model card | link | |
| K2-Horizon-3.7B | 50.9 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 49.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| LFM2.5-8B-A1B | 64.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Nex-N2.5-mini | 83.4 | % | Hugging Face model card | link | |
| Ling-3.0-flash | 82 | % | multi-agent | Hugging Face model card | link |
| DeepSeek-V4-Flash-DSpark | 73.2 | % | Pass@1 | Hugging Face model card | link |
| Ornith-1.5-35B-A3B | 67.6 | % | Hugging Face model card | link | |
| K2-Horizon-7B | 59 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 56.4 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 48.6 | % | pass@1, w/o HI | Hugging Face model card | link |
| Spark-X2.5-4B | 40.9 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 39.7 | % | Top100 | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 37.0 | % | Overall | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 86.2 | % | EM | Hugging Face model card | link |
| MiniCPM-V-4.7-35B-A3B | 83.5 | % | instruct | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 81.9 | % | Overall | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 79.2 | % | w/o HI | Hugging Face model card | link |
| diffusiongemma-26B-A4B-it | 77.6 | % | Hugging Face model card | link | |
| granite-4.2-30b | 77.6 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 77.2 | % | Hugging Face model card | link | |
| granite-4.2-8b | 74.0 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 70.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Muse-Glimmer-30B | 75.5 | % | Public | Hugging Face model card | link |
| Ornith-1.5-35B-A3B | 70.2 | % | Hugging Face model card | link | |
| DeepSeek-V4-Flash-DSpark | 69 | % | Pass@1 | Hugging Face model card | link |
| Ling-3.0-flash | 65.5 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 57.8 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 54.6 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 54.2 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 45.6 | % | w/o HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| MiniCPM5-2B | 97.1 | % | Telecom | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 96.0 | % | Telecom, avg@4, w/ HI | Hugging Face model card | link |
| LFM2.5-8B-A1B | 88.1 | % | Telecom | Hugging Face model card | link |
| MiniCPM-V-4.7-35B-A3B | 84.7 | % | instruct | Hugging Face model card | link |
| Spark-X2.5-4B | 75.1 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 69 | % | average over 3 | Hugging Face model card | link |
| diffusiongemma-26B-A4B-it | 56.2 | % | average over 3 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 90.6 | % | RQ, with CI | Hugging Face model card | link |
| Qwen3.8-27B | 90.2 | % | RQ with CI | Hugging Face model card | link |
| Ling-3.0-flash-VL | 81.3 | % | RQ | Hugging Face model card | link |
| Muse-Glimmer-30B | 78.8 | % | Reasoning | Hugging Face model card | link |
| MiniCPM-V-4.7-35B-A3B | 75.6 | % | Reasoning, 4x compression, instruct | Hugging Face model card | link |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 63.6 | % | Chart Reasoning | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 88.4 | % | Pass@1 | Hugging Face model card | link |
| Ling-3.0-flash | 83.7 | % | Hugging Face model card | link | |
| Spark-X2.5-4B | 74.2 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 71.0 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 67.3 | % | Hugging Face model card | link | |
| LongCat-Flash-Lite-Sparse | 49.4 | % | avg@4, w/o HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 95.7 | % | with CI | Hugging Face model card | link |
| Qwen3.8-27B | 94.6 | % | with CI | Hugging Face model card | link |
| Ling-3.0-flash-VL | 84.9 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 79.7 | % | Hugging Face model card | link | |
| MiniCPM-V-4.7-35B-A3B | 74.2 | % | 4x visual token compression, instruct | Hugging Face model card | link |
| diffusiongemma-26B-A4B-it | 70.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 58.7 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 42.2 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 36.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Laguna-S-2.1 | 40.4 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 22 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash-VL | 79 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 74 | % | Hugging Face model card | link | |
| MiniCPM-V-4.7-35B-A3B | 69.7 | % | 4x visual token compression, instruct | Hugging Face model card | link |
| gemma-4-12B-it | 69.1 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 54.3 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 90.8 | % | 128K | Hugging Face model card | link |
| DeepSeek-V4-Flash-DSpark | 78.7 | % | 1M | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 44.7 | % | 8-needle, w/o HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| gemma-4-12B-it | 43.4 | % | 8 needle 128k (average) | Hugging Face model card | link |
| diffusiongemma-26B-A4B-it | 32 | % | 8 needle 128k (average) | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash-VL | 91.3 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 91.1 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 75.8 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 0.3 | avg edit distance | Hugging Face model card | link | |
| gemma-4-12B-it | 0.2 | avg edit distance | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Nex-N2.5-mini | 1446 | points | Overall | Hugging Face model card | link |
| Muse-Glimmer-30B | 953 | points | Overall | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 832 | points | Overall | Hugging Face model card | link |
| MiniCPM5-2B | 19.6 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Spark-X2.5-4B | 93 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 91.8 | % | Hugging Face model card | link | |
| Hy-MT2-30B-A3B | 89.8 | % | Overall | Official tech report / arXiv paper | link |
| MiniCPM5-2B | 86.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 87.7 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 83.2 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 79.9 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 71.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 48.1 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 46.2 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 42.3 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 32.4 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 73.5 | % | Verified, Pass@1 | Hugging Face model card | link |
| Laguna-S-2.1 | 49.7 | % | Verified | Hugging Face model card | link |
| Ornith-1.5-35B-A3B | 48.7 | % | Verified | Hugging Face model card | link |
| DeepSeek-V4-Flash-DSpark | 47.8 | % | Pass@1 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 64 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 62.9 | % | Hugging Face model card | link | |
| Ling-3.0-flash-VL | 57.7 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 52.9 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Agnes-3.0-Flash | 23 | % | Hugging Face model card | link | |
| K2-Horizon-MoVA-36B-A4B | 18.8 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 8.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ornith-1.5-35B-A3B | 72.5 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 66.5 | % | Hugging Face model card | link | |
| Nanbeige4.2-3B | 52.2 | % | pass^3 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 64.4 | % | Pass@3 | Hugging Face model card | link |
| Ling-3.0-flash-VL | 59.9 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 57.4 | % | pass@3 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 3052 | rating | Hugging Face model card | link | |
| gemma-4-12B-it | 1659 | rating | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 1429 | rating | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 1225 | score | Hugging Face model card | link | |
| granite-4.2-8b | 1189 | points | Hugging Face model card | link | |
| Nanbeige4.2-3B | 74.3 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash-DSpark | 1395 | Elo | Hugging Face model card | link | |
| Ling-3.0-flash | 1107 | points | v2 | Hugging Face model card | link |
| Ling-3.0-tiny | 772 | points | v2 | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 55.7 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 33.4 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 28.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| LongCat-Flash-Lite-Sparse | 96.8 | % | w/ HI | Hugging Face model card | link |
| MiniCPM5-2B | 94.6 | % | Hugging Face model card | link | |
| LFM2.5-8B-A1B | 88.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-27B | 84.3 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 71.2 | % | NexCUA harness | Hugging Face model card | link |
| Muse-Glimmer-30B | 65.9 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 73.6 | % | Hugging Face model card | link | |
| Ornith-1.5-35B-A3B | 67.8 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 59.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 51.2 | score | Score | Hugging Face model card | link |
| Qwen3.8-27B | 42.9 | % | score | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 84.5 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 81.9 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 67.9 | % | Hugging Face model card | link | |
| granite-4.2-8b | 65.2 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 77 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 47.9 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| gemma-4-12B-it | 53 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 47.6 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 41.9 | % | Hugging Face model card | link | |
| granite-4.2-8b | 41.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| LongCat-Flash-Lite-Sparse | 61.9 | % | pass@1, w/o HI | Hugging Face model card | link |
| MiniCPM5-2B | 43.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B | 90.2 | % | instruct | Hugging Face model card | link |
| LongCat-Flash-Lite-Sparse | 84.5 | % | w/ HI | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Nanbeige4.2-3B | 65 | % | Hugging Face model card | link | |
| MiniCPM5-2B | 59.2 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 73.9 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 70.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 72.3 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 65.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 77.3 | % | Hugging Face model card | link | |
| Ling-3.0-tiny | 62.3 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| LongCat-Flash-Lite-Sparse | 53.6 | % | w/ HI | Hugging Face model card | link |
| MiniCPM5-2B | 43.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 66.6 | % | Hugging Face model card | link | |
| granite-4.2-8b | 61.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| gemma-4-12B-it | 83.4 | % | Hugging Face model card | link | |
| diffusiongemma-26B-A4B-it | 81.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| diffusiongemma-26B-A4B-it | 49 | % | Hugging Face model card | link | |
| gemma-4-12B-it | 48.7 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B | 68.5 | % | 4x visual token compression, instruct | Hugging Face model card | link |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 67.0 | % | EN | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 52.3 | % | 2.0, Partial | Hugging Face model card | link |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 47.4 | % | Computer Use | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| KAT-Coder-V2.5-Dev | 93.4 | % | pass@1 | Hugging Face model card | link |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 85.4 | % | Overall | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 42.9 | % | Hugging Face model card | link | |
| granite-4.2-8b | 41.2 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| granite-4.2-30b | 90.0 | % | 64K | Hugging Face model card | link |
| granite-4.2-8b | 81.0 | % | 64K | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 88.5 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 85.9 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | 49.9 | % | Hugging Face model card | link | |
| Qwen3.8-27B | 47.1 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Laguna-S-2.1 | 46.2 | % | Codebase QnA | Hugging Face model card | link |
| Ornith-1.5-35B-A3B | 39.8 | % | QnA | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-27B | 38.6 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 25.5 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Ling-3.0-flash | 44.8 | % | Hugging Face model card | link | |
| Muse-Glimmer-30B | 44.3 | % | with skills | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B | 61.2 | % | instruct | Hugging Face model card | link |
| MiniCPM5-2B | 40.8 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Nex-N2.5-mini | 54.6 | % | Hugging Face model card | link | |
| Ornith-1.5-9B | 41.2 | % | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B | 76.4 | % | w/o subtitles, 4x compression, instruct | Hugging Face model card | link |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 72.2 | % | Video Q/A | Hugging Face model card | link |
| Model | Score | Metric | Subtask | Source | URL |
|---|---|---|---|---|---|
| Qwen3.8-27B | 64.8 | % | Hugging Face model card | link | |
| Nex-N2.5-mini | 63.4 | % | NexCUA harness | Hugging Face model card | link |