Model comparison
Gemini 3 Pro vs Mistral Large
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 31.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
Google
Mistral AISummary
- They share 33 benchmarks with published results for both. Gemini 3 Pro scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 15.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 91.4% for Gemini 3 Pro and 8.5% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Pro | Mistral Large | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 54.8 | 31.9 |
| Released | 2025-11-18 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 67 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 3 Pro: 51.6 (#39), Mistral Large: 34.3 (#240)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| LMArena Coding | 1481 | 1277 |
| ALE-Bench | 1,177 | 264.7 |
| SWE-bench Verified | 72.9% | — |
| SWE-bench Verified (bash only) | 74.2% | — |
| LMArena WebDev | 1440 | — |
| SWE-bench Multilingual | 68.7% | — |
| SciCode | — | 36.2% |
| GSO | 18.6% | — |
| WeirdML | 69.9% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| AlgoTune | 1.83 | — |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 3 Pro: 40.6 (#23), Mistral Large: 28.6 (#89)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.5% | 38.4% |
| Terminal-Bench | 69.4% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#31), Mistral Large: 15.8 (#310)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| SimpleBench | 76.4% | 22.5% |
| CritPt | 6.9% | 0% |
| LMArena Hard Prompts | 1480 | 1257 |
| Epoch Capabilities Index | 152.92 | 128.52 |
| ForecastBench | 61.2 | 57.1 |
| ARC-AGI-2 | 31.1% | — |
| Kagi LLM Benchmark | 80.1% | — |
| NYT Connections (extended) | 94.4% | — |
| ARC-AGI-1 | 75% | — |
| Chess Puzzles | 31% | — |
| EnigmaEval | 18.2% | — |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| LiveBench | — | 48.4% |
Math Gemini 3 Pro leads
Gemini 3 Pro: 49.9 (#59), Mistral Large: 18.2 (#291)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 8.5% |
| Omni-MATH | 55.5% | 28.1% |
| LMArena Math | 1476 | 1262 |
| FrontierMath (Feb 2025 set) | 37.6% | 0.3% |
| MathArena Final-Answer Competitions | 67% | — |
| ProofBench | 20% | — |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.4 (#16), Mistral Large: 30.1 (#230)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| GPQA Diamond | 92.6% | 51.3% |
| MMLU-Pro | 90.3% | 59.9% |
| Vectara Hallucination Rate | 13.6% | 4.5% |
| GPQA (HELM) | 80.3% | 43.5% |
| LMArena Expert | 1475 | 1232 |
| Humanity's Last Exam | 37.5% | — |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |
Multimodal Not comparable
Gemini 3 Pro: 57.6 (#2), Mistral Large: —
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| LMArena Vision | 1305 | — |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| LMArena Document | 1434 | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#16), Mistral Large: 40.0 (#219)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| LMArena Non-English | 1474 | 1237 |
| LMArena Chinese | 1523 | 1240 |
| LMArena French | 1492 | 1325 |
| LMArena German | 1515 | 1254 |
| LMArena Japanese | 1510 | 1188 |
| LMArena Korean | 1448 | 1202 |
| LMArena Russian | 1493 | 1257 |
| LMArena Spanish | 1470 | 1268 |
Instruction Following Gemini 3 Pro leads
Gemini 3 Pro: 76.3 (#45), Mistral Large: 67.9 (#191)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| IFEval | 87.7% | 87.7% |
| LMArena Instruction Following | 1458 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Gemini 3 Pro leads
Gemini 3 Pro: 44.0 (#79), Mistral Large: 38.3 (#199)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1471 | 1261 |
| CL-bench | 15.8% | — |
Writing & Preference Gemini 3 Pro leads
Gemini 3 Pro: 66.4 (#35), Mistral Large: 40.7 (#242)
| Benchmark | Gemini 3 Pro | Mistral Large |
|---|---|---|
| LMArena Text | 1479 | 1266 |
| LMArena Creative Writing | 1482 | 1243 |
| EQ-Bench Creative Writing | 1525 | 985 |
| WildBench | 85.9% | 80.1% |
| LMArena Multi-Turn | 1484 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Gemini 3 Pro better than Mistral Large?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 31.9 on the Noometry Index.
Is Gemini 3 Pro or Mistral Large better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 34.3 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and Mistral Large share?
33 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Mistral Large has 51.