Model comparison
gpt-oss-20b vs Mistral Large 4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 29× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AISummary
- They share 12 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Mistral Large 4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Mistral Large 4 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 32.5 | 43.1 |
| Released | 2025-08-05 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 16K | 262K |
| Input $ / M tokens | $0.018 | $0.68 |
| Output $ / M tokens | $0.09 | $2.09 |
| Results tracked | 34 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
gpt-oss-20b: 37.6 (#192), Mistral Large 4: 48.6 (#57)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1306 | 1475 |
| LMArena WebDev | — | 1541 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Mistral Large 4: —
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Mistral Large 4 leads
gpt-oss-20b: 19.3 (#261), Mistral Large 4: 22.5 (#192)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1444 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 27.4% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math Mistral Large 4 leads
gpt-oss-20b: 39.4 (#103), Mistral Large 4: 40.4 (#91)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1317 | 1488 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Mistral Large 4 leads
gpt-oss-20b: 34.6 (#195), Mistral Large 4: 36.6 (#166)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Expert | 1258 | 1447 |
| GPQA Diamond | 60.8% | — |
| SimpleQA Verified | — | 20% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Mistral Large 4 leads
gpt-oss-20b: 42.2 (#197), Mistral Large 4: 52.6 (#82)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1268 | 1415 |
| LMArena Chinese | 1314 | 1491 |
| LMArena Russian | 1278 | 1414 |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Mistral Large 4 leads
gpt-oss-20b: 61.8 (#240), Mistral Large 4: 75.0 (#76)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1424 |
| IFEval | 73.2% | — |
Long Context Mistral Large 4 leads
gpt-oss-20b: 37.9 (#209), Mistral Large 4: 43.6 (#89)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1250 | 1429 |
Writing & Preference Mistral Large 4 leads
gpt-oss-20b: 35.5 (#265), Mistral Large 4: 60.4 (#97)
| Benchmark | gpt-oss-20b | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1287 | 1427 |
| LMArena Creative Writing | 1201 | 1361 |
| LMArena Multi-Turn | 1268 | 1424 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Mistral Large 4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 29× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Mistral Large 4?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is gpt-oss-20b or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 131K.
How many benchmarks do gpt-oss-20b and Mistral Large 4 share?
12 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Mistral Large 4 has 15.