Model comparison
Claude 3.5 Haiku vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.2 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and gpt-oss-120b in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku 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 Haiku | gpt-oss-120b | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.2 | 36.3 |
| Released | 2024-10-22 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 49 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Haiku: 32.9 (#265), gpt-oss-120b: 33.5 (#256)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| Aider Polyglot | 28% | 41.8% |
| SciCode | 27.4% | 36% |
| WeirdML | 30.7% | 48.2% |
| LMArena Coding | 1286 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Claude 3.5 Haiku leads
Claude 3.5 Haiku: 28.0 (#95), gpt-oss-120b: 12.2 (#153)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| BALROG | 19.3% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
Claude 3.5 Haiku: 17.7 (#290), gpt-oss-120b: 20.0 (#245)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| CritPt | 0% | 1.1% |
| LMArena Hard Prompts | 1251 | 1364 |
| DTBench | 56.7% | 76.3% |
| Epoch Capabilities Index | 127.15 | 139.93 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 2% |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| LiveBench | 43.5% | — |
Math gpt-oss-120b leads
Claude 3.5 Haiku: 14.7 (#300), gpt-oss-120b: 52.5 (#50)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 88.9% |
| Omni-MATH | 22.4% | 68.8% |
| LMArena Math | 1244 | 1389 |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge gpt-oss-120b leads
Claude 3.5 Haiku: 18.7 (#281), gpt-oss-120b: 42.4 (#96)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 38.1% | 75.8% |
| MMLU-Pro | 60.5% | 79.5% |
| Confabulations | 36.7% | 15.7% |
| GPQA (HELM) | 36.3% | 68.4% |
| LMArena Expert | 1208 | 1356 |
| Vectara Hallucination Rate | — | 14.2% |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), gpt-oss-120b: —
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual gpt-oss-120b leads
Claude 3.5 Haiku: 40.0 (#218), gpt-oss-120b: 48.0 (#147)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1238 | 1351 |
| LMArena Chinese | 1229 | 1385 |
| LMArena French | 1264 | 1369 |
| LMArena German | 1237 | 1353 |
| LMArena Japanese | 1175 | 1331 |
| LMArena Korean | 1173 | 1282 |
| LMArena Russian | 1253 | 1343 |
| LMArena Spanish | 1261 | 1389 |
Instruction Following gpt-oss-120b leads
Claude 3.5 Haiku: 62.9 (#234), gpt-oss-120b: 69.3 (#173)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| IFEval | 79.2% | 83.6% |
| LMArena Instruction Following | 1241 | 1318 |
| LiveBench Instruction Following | 61.9% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), gpt-oss-120b: 31.4 (#278)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1261 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Claude 3.5 Haiku: 42.7 (#234), gpt-oss-120b: 46.5 (#217)
| Benchmark | Claude 3.5 Haiku | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1255 | 1365 |
| LMArena Creative Writing | 1233 | 1275 |
| Short-Story Creative Writing | 73.5% | 77.1% |
| EQ-Bench Creative Writing | 1146 | 961 |
| WildBench | 76% | 84.5% |
| LMArena Multi-Turn | 1265 | 1340 |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku 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 3.5 Haiku and gpt-oss-120b share?
33 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and gpt-oss-120b has 48.