Model comparison
Claude 2.1 vs gpt-oss-20b
gpt-oss-20b is the stronger model overall, scoring 32.5 to 25.2 on the Noometry Index.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and gpt-oss-20b in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 10.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.9% for Claude 2.1 and 65.3% for gpt-oss-20b.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | gpt-oss-20b | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.2 | 32.5 |
| Released | 2023-11-21 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 7 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Claude 2.1: 26.2 (#327), gpt-oss-20b: 37.6 (#192)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| WeirdML | 7.1% | 40.9% |
| SciCode | — | 34.4% |
| LMArena Coding | — | 1306 |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
Claude 2.1: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), gpt-oss-20b: 19.3 (#261)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| DTBench | 51% | 68% |
| Epoch Capabilities Index | 119.27 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | — | 1274 |
| LMCA | — | 14.5% |
| ForecastBench | 54.2 | — |
Math gpt-oss-20b leads
Claude 2.1: 10.2 (#315), gpt-oss-20b: 39.4 (#103)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 65.3% |
| Omni-MATH | — | 56.5% |
| LMArena Math | — | 1317 |
Knowledge gpt-oss-20b leads
Claude 2.1: 15.4 (#292), gpt-oss-20b: 34.6 (#195)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 33% | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |
| MMLU | 73.5% | — |
Multilingual Not comparable
Claude 2.1: —, gpt-oss-20b: 42.2 (#197)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | — | 1268 |
| LMArena Chinese | — | 1314 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Russian | — | 1278 |
| LMArena Spanish | — | 1267 |
Instruction Following Not comparable
Claude 2.1: —, gpt-oss-20b: 61.8 (#240)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| IFEval | — | 73.2% |
| LMArena Instruction Following | — | 1236 |
Long Context Not comparable
Claude 2.1: —, gpt-oss-20b: 37.9 (#209)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | — | 1250 |
Writing & Preference Not comparable
Claude 2.1: —, gpt-oss-20b: 35.5 (#265)
| Benchmark | Claude 2.1 | gpt-oss-20b |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1201 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
| LMArena Multi-Turn | — | 1268 |
Frequently asked questions
Is Claude 2.1 better than gpt-oss-20b?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 25.2 on the Noometry Index.
Is Claude 2.1 or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and gpt-oss-20b share?
5 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and gpt-oss-20b has 34.