Model comparison
gpt-oss-20b vs Mistral Large
gpt-oss-20b and Mistral Large score almost the same on the Noometry Index (32.5 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 30 shared benchmarks.
Mistral AISummary
- They share 30 benchmarks with published results for both. gpt-oss-20b scores higher in 5 categories and Mistral Large in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 8.5% for Mistral Large.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $2 / $6 for Mistral Large.
Side by side
| gpt-oss-20b | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 31.9 |
| Released | 2025-08-05 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $0.018 | $2 |
| Output $ / M tokens | $0.09 | $6 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Mistral Large: 34.3 (#240)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| SciCode | 34.4% | 36.2% |
| LMArena Coding | 1306 | 1277 |
| ALE-Bench | 566.05 | 264.7 |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
gpt-oss-20b: 9.3 (#154), Mistral Large: 28.6 (#89)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning gpt-oss-20b leads
gpt-oss-20b: 19.3 (#261), Mistral Large: 15.8 (#310)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| CritPt | 1.4% | 0% |
| LMArena Hard Prompts | 1274 | 1257 |
| DTBench | 68% | 65.1% |
| LMCA | 14.5% | 16.7% |
| Epoch Capabilities Index | 137.82 | 128.52 |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 53.2% | — |
| Chess Puzzles | 4% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Mistral Large: 18.2 (#291)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 8.5% |
| Omni-MATH | 56.5% | 28.1% |
| LMArena Math | 1317 | 1262 |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Mistral Large: 30.1 (#230)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| GPQA Diamond | 60.8% | 51.3% |
| MMLU-Pro | 74% | 59.9% |
| GPQA (HELM) | 59.4% | 43.5% |
| LMArena Expert | 1258 | 1232 |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| MMLU | — | 80% |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.2 (#197), Mistral Large: 40.0 (#219)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| LMArena Non-English | 1268 | 1237 |
| LMArena Chinese | 1314 | 1240 |
| LMArena German | 1255 | 1254 |
| LMArena Japanese | 1244 | 1188 |
| LMArena Korean | 1236 | 1202 |
| LMArena Russian | 1278 | 1257 |
| LMArena Spanish | 1267 | 1268 |
| LMArena French | — | 1325 |
Instruction Following Mistral Large leads
gpt-oss-20b: 61.8 (#240), Mistral Large: 67.9 (#191)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| IFEval | 73.2% | 87.7% |
| LMArena Instruction Following | 1236 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Too close to call
gpt-oss-20b: 37.9 (#209), Mistral Large: 38.3 (#199)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1250 | 1261 |
Writing & Preference Mistral Large leads
gpt-oss-20b: 35.5 (#265), Mistral Large: 40.7 (#242)
| Benchmark | gpt-oss-20b | Mistral Large |
|---|---|---|
| LMArena Text | 1287 | 1266 |
| LMArena Creative Writing | 1201 | 1243 |
| EQ-Bench Creative Writing | 666 | 985 |
| WildBench | 73.7% | 80.1% |
| LMArena Multi-Turn | 1268 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is gpt-oss-20b better than Mistral Large?
gpt-oss-20b and Mistral Large score almost the same on the Noometry Index (32.5 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, gpt-oss-20b or Mistral Large?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Large lists at $2 and $6.
Is gpt-oss-20b or Mistral Large better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do gpt-oss-20b and Mistral Large share?
30 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Large has 51.