Model comparison
GPT-5 Pro vs Mistral Medium
GPT-5 Pro is the stronger model overall, scoring 46.2 to 36.0 on the Noometry Index. Mistral Medium costs 14× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. GPT-5 Pro scores higher in 4 categories and Mistral Medium in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Pro leads 56.2 to 24.9.
- The biggest single-benchmark swing is Humanity's Last Exam: 31.6% for GPT-5 Pro and 4.5% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Pro | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 46.2 | 36.0 |
| Released | 2025-10-06 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 272K | 262K |
| Input $ / M tokens | $15 | $1.50 |
| Output $ / M tokens | $120 | $7.50 |
| Results tracked | 12 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 43.4 (#77), Mistral Medium: 33.8 (#241)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| WeirdML | 60.4% | 43.7% |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| LMArena Coding | — | 1434 |
| ALE-Bench | — | 763.98 |
| AlgoTune | 1.31 | — |
Agentic & Tool Use Not comparable
GPT-5 Pro: —, Mistral Medium: 28.1 (#84)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 39.2 (#52), Mistral Medium: 23.3 (#165)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 76.8% | 50% |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| ARC-AGI-1 | 70.2% | — |
| CritPt | — | 0% |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 150.26 | — |
Math GPT-5 Pro leads
GPT-5 Pro: 48.0 (#53), Mistral Medium: 27.2 (#238)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LMArena Math | — | 1409 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.2 (#39), Mistral Medium: 24.9 (#260)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| Humanity's Last Exam | 31.6% | 4.5% |
| GPQA Diamond | — | 59.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
GPT-5 Pro: —, Mistral Medium: 34.6 (#82)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Not comparable
GPT-5 Pro: —, Mistral Medium: 52.3 (#86)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena German | — | 1433 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1382 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Not comparable
GPT-5 Pro: —, Mistral Medium: 73.9 (#111)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |
Long Context Not comparable
GPT-5 Pro: —, Mistral Medium: 42.9 (#108)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Not comparable
GPT-5 Pro: —, Mistral Medium: 60.2 (#97)
| Benchmark | GPT-5 Pro | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is GPT-5 Pro better than Mistral Medium?
GPT-5 Pro is the stronger model overall, scoring 46.2 to 36.0 on the Noometry Index. Mistral Medium costs 14× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Pro or Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Pro or Mistral Medium better for coding?
GPT-5 Pro scores higher on coding benchmarks: 43.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Pro and Mistral Medium share?
3 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Mistral Medium has 36.