Model comparison
GPT-4.5 vs Mistral Medium
GPT-4.5 and Mistral Medium score almost the same on the Noometry Index (37.2 vs 36.3), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and Mistral Medium in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Medium leads 24.0 to 13.9.
- The biggest single-benchmark swing is GPQA Diamond: 68.7% for GPT-4.5 and 59.5% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 37.2 | 36.3 |
| Released | 2025-02-27 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 42 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Mistral Medium: 34.2 (#243)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| WeirdML | 39.4% | 43.7% |
| LMArena Coding | 1396 | 1434 |
| FrontierCode | — | 8% |
| Aider Polyglot | 44.9% | — |
| SciCode | — | 40.2% |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Too close to call
GPT-4.5: 27.9 (#97), Mistral Medium: 28.3 (#90)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| Cybench | 17.5% | — |
Reasoning Mistral Medium leads
GPT-4.5: 13.9 (#330), Mistral Medium: 24.0 (#167)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1426 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 50% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 0% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| DTBench | — | 75.5% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math GPT-4.5 leads
GPT-4.5: 32.6 (#211), Mistral Medium: 28.1 (#245)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 32.2% |
| LMArena Math | 1412 | 1408 |
| MATH Level 5 | 78.6% | 81.6% |
| ProofBench | — | 9% |
| LiveBench Math | 69.3% | — |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-4.5 leads
GPT-4.5: 32.5 (#211), Mistral Medium: 25.0 (#265)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 68.7% | 59.5% |
| Humanity's Last Exam | 5.4% | 4.5% |
| LMArena Expert | 1394 | 1408 |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal GPT-4.5 leads
GPT-4.5: 37.6 (#71), Mistral Medium: 35.3 (#88)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1195 | 1172 |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.5 (#83), Mistral Medium: 52.1 (#91)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1413 | 1408 |
| LMArena Chinese | 1421 | 1447 |
| LMArena French | 1418 | 1459 |
| LMArena German | 1457 | 1432 |
| LMArena Japanese | 1416 | 1378 |
| LMArena Korean | 1392 | 1380 |
| LMArena Russian | 1419 | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
GPT-4.5: 72.6 (#134), Mistral Medium: 73.7 (#116)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1404 | 1398 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Mistral Medium leads
GPT-4.5: 40.4 (#155), Mistral Medium: 42.9 (#114)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1406 | 1406 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Mistral Medium leads
GPT-4.5: 56.9 (#134), Mistral Medium: 60.0 (#103)
| Benchmark | GPT-4.5 | Mistral Medium |
|---|---|---|
| LMArena Text | 1417 | 1424 |
| LMArena Creative Writing | 1394 | 1391 |
| Short-Story Creative Writing | 75.6% | 77.3% |
| LMArena Multi-Turn | 1444 | 1418 |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Mistral Medium?
GPT-4.5 and Mistral Medium score almost the same on the Noometry Index (37.2 vs 36.3), so choose on price, context window or the category you care about most.
Is GPT-4.5 or Mistral Medium better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 34.2 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Mistral Medium share?
23 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Mistral Medium has 36.