Model comparison
Claude 3.5 Sonnet vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.0 to 34.4 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 5 categories and gpt-oss-120b in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 88.9% for gpt-oss-120b.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | gpt-oss-120b | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.4 | 36.0 |
| Released | 2024-06-20 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 60 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.5 (#145), gpt-oss-120b: 33.2 (#251)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| Aider Polyglot | 51.6% | 41.8% |
| WeirdML | 40% | 48.2% |
| LMArena Coding | 1343 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| SciCode | — | 36% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.1 (#61), gpt-oss-120b: 12.1 (#145)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| METR Time Horizons | 45.2% | 56.6% |
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| Vending-Bench 2 | — | -21.53 |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), gpt-oss-120b: 19.5 (#236)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| SimpleBench | 41.4% | 22.1% |
| LMArena Hard Prompts | 1305 | 1364 |
| DTBench | 67.8% | 76.3% |
| Epoch Capabilities Index | 133.55 | 139.94 |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math gpt-oss-120b leads
Claude 3.5 Sonnet: 18.0 (#282), gpt-oss-120b: 50.6 (#43)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 88.9% |
| Omni-MATH | 27.6% | 68.8% |
| LMArena Math | 1306 | 1388 |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge gpt-oss-120b leads
Claude 3.5 Sonnet: 28.5 (#236), gpt-oss-120b: 42.3 (#89)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 55.3% | 75.8% |
| MMLU-Pro | 77.7% | 79.5% |
| Confabulations | 19.9% | 15.7% |
| GPQA (HELM) | 56.5% | 68.4% |
| LMArena Expert | 1264 | 1356 |
| Humanity's Last Exam | 4.1% | — |
| Vectara Hallucination Rate | — | 14.2% |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), gpt-oss-120b: —
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual gpt-oss-120b leads
Claude 3.5 Sonnet: 43.4 (#180), gpt-oss-120b: 48.2 (#142)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1283 | 1350 |
| LMArena Chinese | 1271 | 1384 |
| LMArena French | 1304 | 1370 |
| LMArena German | 1297 | 1355 |
| LMArena Japanese | 1234 | 1332 |
| LMArena Korean | 1200 | 1283 |
| LMArena Russian | 1305 | 1343 |
| LMArena Spanish | 1289 | 1388 |
Instruction Following Too close to call
Claude 3.5 Sonnet: 69.0 (#177), gpt-oss-120b: 69.5 (#168)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| IFEval | 85.5% | 83.6% |
| LMArena Instruction Following | 1297 | 1318 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#162), gpt-oss-120b: 31.4 (#273)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1311 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 53.0 (#159), gpt-oss-120b: 46.7 (#213)
| Benchmark | Claude 3.5 Sonnet | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1298 | 1366 |
| LMArena Creative Writing | 1292 | 1274 |
| Short-Story Creative Writing | 80.3% | 77.1% |
| EQ-Bench Creative Writing | 1451 | 961 |
| WildBench | 79.2% | 84.5% |
| LMArena Multi-Turn | 1326 | 1340 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.0 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or gpt-oss-120b better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 33.2 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and gpt-oss-120b share?
33 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and gpt-oss-120b has 48.