Model comparison
GPT-4.5 vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 38.6 to 36.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Mistral Large 3 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-4.5 leads 41.8 to 34.1.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.9 | 38.6 |
| Released | 2025-02-27 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 42 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 41.8 (#102), Mistral Large 3: 34.1 (#230)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1397 | 1447 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1230 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), Mistral Large 3: —
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Too close to call
GPT-4.5: 14.1 (#320), Mistral Large 3: 14.6 (#314)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1429 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Mistral Large 3 leads
GPT-4.5: 31.0 (#200), Mistral Large 3: 36.0 (#131)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1412 | 1415 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Mistral Large 3 leads
GPT-4.5: 32.4 (#205), Mistral Large 3: 35.5 (#173)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1394 | 1421 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Too close to call
GPT-4.5: 37.0 (#68), Mistral Large 3: 37.6 (#65)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1195 | 1222 |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.7 (#78), Mistral Large 3: 52.6 (#79)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1413 | 1412 |
| LMArena Chinese | 1421 | 1448 |
| LMArena French | 1417 | 1456 |
| LMArena German | 1457 | 1438 |
| LMArena Japanese | 1416 | 1399 |
| LMArena Korean | 1392 | 1384 |
| LMArena Russian | 1419 | 1412 |
| LMArena Spanish | — | 1437 |
Instruction Following Mistral Large 3 leads
GPT-4.5: 72.8 (#129), Mistral Large 3: 74.1 (#104)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1402 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Mistral Large 3 leads
GPT-4.5: 40.4 (#150), Mistral Large 3: 43.1 (#102)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1413 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Mistral Large 3 leads
GPT-4.5: 57.1 (#129), Mistral Large 3: 60.2 (#100)
| Benchmark | GPT-4.5 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1417 | 1427 |
| LMArena Creative Writing | 1394 | 1385 |
| EQ-Bench Creative Writing | 1258 | 1412 |
| LMArena Multi-Turn | 1444 | 1429 |
| Short-Story Creative Writing | 75.6% | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 38.6 to 36.9 on the Noometry Index.
Is GPT-4.5 or Mistral Large 3 better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 34.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Mistral Large 3 share?
18 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Mistral Large 3 has 24.