Scientific Coding on SciCode
0.4275Accuracygpt-oss-120B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| gpt-oss-120BReasoning effort=Medium, KV cache precision=FP82026.02 | 0.4275 | — | — | — | |
| gpt-oss-120BReasoning effort=High, KV cache precision=BF162026.02 | 0.4172 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=FP82026.02 | 0.4142 | — | — | — | |
| gpt-oss-120BReasoning effort=Medium, KV cache precision=BF162026.02 | 0.4142 | — | — | — | |
| gpt-oss-120BReasoning effort=High, KV cache precision=FP82026.02 | 0.4083 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=BF162026.02 | 0.4083 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=FP82026.02 | 0.4009 | — | — | — | |
| gpt-oss-120BReasoning effort=Low, KV cache precision=FP82026.02 | 0.4009 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=BF162026.02 | 0.3964 | — | — | — | |
| gpt-oss-120BReasoning effort=Low, KV cache precision=BF162026.02 | 0.392 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=FP82026.02 | 0.3846 | — | — | — | |
| gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=BF162026.02 | 0.3817 | — | — | — | |
| Nemotron 3 Nano 30B-A3BOpen-Source=✓, Size=30B-A3B2026.04 | 0.333 | — | — | — | |
| BF16Precision=BF16, Backbone=Nemotron 3 Nano2026.01 | 0.33 | — | — | — | |
| NVFP4 QADPrecision=NVFP4, Type=QAD, Backbone=Nemotron 3 Nano2026.01 | 0.323 | — | — | — | |
| Nemotron 3 Nano OmniOpen-Source=✓, Size=30B-A3B2026.04 | 0.32 | — | — | — | |
| NVFP4 PTQPrecision=NVFP4, Type=PTQ, Backbone=Nemotron 3 Nano2026.01 | 0.305 | — | — | — | |
| NVFP4 QATPrecision=NVFP4, Type=QAT, Backbone=Nemotron 3 Nano2026.01 | 0.258 | — | — | — | |
| Claude Opus 4.82026.06 | — | — | — | 53.5 | |
| DS-v4-FlashSubtask setting=subtask, Parameter Count=284B-A13B2026.06 | — | — | — | 48.2 | |
| DS-v4-ProSubtask setting=subtask, Parameter Count=1.6T-A49B2026.06 | — | — | — | 50.5 | |
| Fugu2026.06 | — | — | — | 60.1 | |
| Fugu-Ultra2026.06 | — | — | — | 58.7 | |
| Gemini 3.12026.06 | — | — | — | 58.9 | |
| GLM-5.1Subtask setting=subtask, Parameter Count=744B-A40B2026.06 | — | — | — | 47.7 | |
| GPT-5Temperature=0, Access=Official API2026.01 | — | 0.85 | 1 | — | |
| GPT-5.52026.06 | — | — | — | 56.1 | |
| GPT-OSS-120BEvaluation level=subtask2026.04 | — | — | — | 39 | |
| Kimi-K2.6Subtask setting=subtask, Parameter Count=1T-A32B2026.06 | — | — | — | 52 | |
| Llama3-8BTemperature=0, Hardware=2 4090 GPUs with 24GB memory2026.01 | — | 0.1 | 5 | — | |
| MiniMax-2.7Subtask setting=subtask, Parameter Count=230B-A10B2026.06 | — | — | — | 38.3 | |
| Nemotron 3 SuperEvaluation level=subtask2026.04 | — | — | — | 42.05 | |
| Nemotron 3 UltraSubtask setting=subtask, Parameter Count=550B-A55B2026.06 | — | — | — | 44.6 | |
| Qwen-3.5Subtask setting=subtask, Parameter Count=397B-17B2026.06 | — | — | — | 48 | |
| Qwen-turboTemperature=0, Access=Official API2026.01 | — | 0.16 | 4 | — | |
| Qwen2.5-32BTemperature=0, Access=Official API2026.01 | — | 0.25 | 3 | — | |
| Qwen2.5-72BTemperature=0, Access=Official API2026.01 | — | 0.28 | 2 | — | |
| Qwen3.5-122B-A10BEvaluation level=subtask2026.04 | — | — | — | 42 |