Model comparison
gpt-oss-120b vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 43× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and Mistral Medium 3.5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 39.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 58.6% for gpt-oss-120b and 41.4% for Mistral Medium 3.5.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-120b | Mistral Medium 3.5 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.3 | 40.2 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 210K |
| Input $ / M tokens | $0.037 | $1.50 |
| Output $ / M tokens | $0.17 | $7.50 |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
gpt-oss-120b: 33.5 (#256), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1380 | 1461 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1264 |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Mistral Medium 3.5: —
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 41.4% |
| LMArena Hard Prompts | 1364 | 1436 |
| Epoch Capabilities Index | 139.93 | 141.35 |
| SimpleBench | 22.1% | — |
| NYT Connections (extended) | — | 12.9% |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1389 | 1431 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1356 | 1432 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multimodal Not comparable
gpt-oss-120b: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Mistral Medium 3.5 leads
gpt-oss-120b: 48.0 (#147), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1351 | 1404 |
| LMArena Chinese | 1385 | 1442 |
| LMArena French | 1369 | 1448 |
| LMArena German | 1353 | 1451 |
| LMArena Korean | 1282 | 1385 |
| LMArena Russian | 1343 | 1395 |
| LMArena Spanish | 1389 | 1409 |
| LMArena Japanese | 1331 | — |
Instruction Following Mistral Medium 3.5 leads
gpt-oss-120b: 69.3 (#173), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1415 |
| IFEval | 83.6% | — |
Long Context Mistral Medium 3.5 leads
gpt-oss-120b: 31.4 (#278), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1319 | 1415 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mistral Medium 3.5 leads
gpt-oss-120b: 46.5 (#217), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | gpt-oss-120b | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1365 | 1421 |
| LMArena Creative Writing | 1275 | 1374 |
| LMArena Multi-Turn | 1340 | 1423 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is gpt-oss-120b better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 43× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Mistral Medium 3.5?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is gpt-oss-120b or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Mistral Medium 3.5 share?
18 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Mistral Medium 3.5 has 22.