Model comparison
GPT-4o vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 28.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. GPT-4o scores higher in 0 categories and Mistral Large 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 10.6.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4o | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 28.6 | 39.1 |
| Released | 2024-05-13 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 16K | 8K |
| Input $ / M tokens | $2.50 | $0.25 |
| Output $ / M tokens | $10 | $0.75 |
| Results tracked | 72 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
GPT-4o: 24.8 (#328), Mistral Large 3: 34.4 (#237)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1297 | 1448 |
| SWE-bench Verified | 31% | — |
| SWE-bench Verified (bash only) | 21.6% | — |
| Aider Polyglot | 45.3% | — |
| LMArena WebDev | — | 1230 |
| GSO | 0% | — |
| WeirdML | 25.1% | — |
| BigCodeBench Instruct | 51.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 61.1% | — |
| CadEval | 26% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o: 21.0 (#141), Mistral Large 3: —
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| GDPval | 9.9% | — |
| TheAgentCompany | 8.6% | — |
| Cybench | 12.5% | — |
| BALROG | 32.3% | — |
| LMArena Search | 1006 | — |
| METR Time Horizons | 40.8% | — |
Reasoning Mistral Large 3 leads
GPT-4o: 9.4 (#343), Mistral Large 3: 15.2 (#319)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1429 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 17.8% | — |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 4.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 13% | — |
| EnigmaEval | 0.8% | — |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 55.8% | — |
| DTBench | 64.5% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 16.6% | — |
| Epoch Capabilities Index | 128.97 | — |
| ForecastBench | 57.7 | — |
| LiveBench | 55.3% | — |
Math Mistral Large 3 leads
GPT-4o: 10.6 (#312), Mistral Large 3: 38.7 (#129)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1285 | 1414 |
| FrontierMath (Tiers 1-3) | 0.4% | — |
| OTIS Mock AIME 2024-2025 | 6.4% | — |
| Omni-MATH | 29.3% | — |
| LiveBench Math | 49.5% | — |
| MATH Level 5 | 53.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Large 3 leads
GPT-4o: 28.8 (#242), Mistral Large 3: 36.0 (#177)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 9.6% | 14.5% |
| LMArena Expert | 1250 | 1421 |
| GPQA Diamond | 49.2% | — |
| Humanity's Last Exam | 2.7% | — |
| SimpleQA Verified | 26% | — |
| MMLU-Pro | 71.3% | — |
| Confabulations | 15.3% | — |
| GPQA (HELM) | 52% | — |
| MMLU | 88.1% | — |
Multimodal Mistral Large 3 leads
GPT-4o: 34.5 (#91), Mistral Large 3: 38.2 (#66)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1137 | 1221 |
| Video-MME | 71.9% | — |
| GeoBench | 71% | — |
| VPCT | 40% | — |
| ScienceQA | 88.5% | — |
Multilingual Mistral Large 3 leads
GPT-4o: 43.2 (#186), Mistral Large 3: 52.5 (#84)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1283 | 1413 |
| LMArena Chinese | 1277 | 1447 |
| LMArena French | 1304 | 1455 |
| LMArena German | 1282 | 1437 |
| LMArena Japanese | 1257 | 1394 |
| LMArena Korean | 1234 | 1384 |
| LMArena Russian | 1286 | 1411 |
| LMArena Spanish | 1292 | 1440 |
Instruction Following Mistral Large 3 leads
GPT-4o: 66.6 (#207), Mistral Large 3: 74.0 (#108)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1278 | 1403 |
| LiveBench Instruction Following | 68.6% | — |
| IFEval | 81.7% | — |
Long Context Mistral Large 3 leads
GPT-4o: 39.4 (#179), Mistral Large 3: 43.1 (#105)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1289 | 1413 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Mistral Large 3 leads
GPT-4o: 52.6 (#166), Mistral Large 3: 60.0 (#101)
| Benchmark | GPT-4o | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1300 | 1428 |
| LMArena Creative Writing | 1292 | 1386 |
| LMArena Multi-Turn | 1302 | 1429 |
| Short-Story Creative Writing | 81.8% | — |
| EQ-Bench Creative Writing | — | 1412 |
| WildBench | 82.8% | — |
| LiveBench Language | 47.6% | — |
Frequently asked questions
Is GPT-4o better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 28.6 on the Noometry Index.
Which is cheaper, GPT-4o or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-4o lists at $2.50 and $10.
Is GPT-4o or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 128K.
How many benchmarks do GPT-4o and Mistral Large 3 share?
19 benchmarks have published results for both models. GPT-4o has 72 scored results on Noometry and Mistral Large 3 has 24.