Model comparison
Claude 3 Opus vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and gpt-oss-120b in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 88.9% for gpt-oss-120b.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | gpt-oss-120b | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 36.3 |
| Released | 2024-02-29 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 46 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Opus: 32.9 (#267), gpt-oss-120b: 33.5 (#256)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| WeirdML | 19.2% | 48.2% |
| LMArena Coding | 1264 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude 3 Opus leads
Claude 3 Opus: 24.6 (#116), gpt-oss-120b: 12.2 (#153)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| METR Time Horizons | 29.5% | 56.6% |
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Cybench | 10% | — |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Claude 3 Opus: 14.6 (#324), gpt-oss-120b: 20.0 (#245)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| SimpleBench | 23.5% | 22.1% |
| Chess Puzzles | 5% | 20% |
| LMArena Hard Prompts | 1245 | 1364 |
| DTBench | 61.6% | 76.3% |
| LMCA | 17% | 22.1% |
| Epoch Capabilities Index | 126.91 | 139.93 |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 57.9% | — |
| Surface Evolver Bench | — | 25% |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math gpt-oss-120b leads
Claude 3 Opus: 14.8 (#299), gpt-oss-120b: 52.5 (#50)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 88.9% |
| LMArena Math | 1273 | 1389 |
| Omni-MATH | — | 68.8% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge gpt-oss-120b leads
Claude 3 Opus: 24.5 (#267), gpt-oss-120b: 42.4 (#96)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 47.2% | 75.8% |
| Confabulations | 22.7% | 15.7% |
| LMArena Expert | 1223 | 1356 |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 79.5% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), gpt-oss-120b: —
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual gpt-oss-120b leads
Claude 3 Opus: 41.4 (#207), gpt-oss-120b: 48.0 (#147)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1258 | 1351 |
| LMArena Chinese | 1248 | 1385 |
| LMArena French | 1275 | 1369 |
| LMArena German | 1258 | 1353 |
| LMArena Japanese | 1204 | 1331 |
| LMArena Korean | 1187 | 1282 |
| LMArena Russian | 1280 | 1343 |
| LMArena Spanish | 1246 | 1389 |
Instruction Following gpt-oss-120b leads
Claude 3 Opus: 64.1 (#228), gpt-oss-120b: 69.3 (#173)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1248 | 1318 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 83.6% |
Long Context Claude 3 Opus leads
Claude 3 Opus: 38.2 (#202), gpt-oss-120b: 31.4 (#278)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1259 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Too close to call
Claude 3 Opus: 47.2 (#213), gpt-oss-120b: 46.5 (#217)
| Benchmark | Claude 3 Opus | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1262 | 1365 |
| LMArena Creative Writing | 1235 | 1275 |
| LMArena Multi-Turn | 1275 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.5 on the Noometry Index.
Is Claude 3 Opus or gpt-oss-120b better for coding?
They score almost the same on coding (32.9 vs 33.5); test both on your own repository before choosing.
How many benchmarks do Claude 3 Opus and gpt-oss-120b share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and gpt-oss-120b has 48.