Model comparison
Gemini 2.0 Flash (Feb 2025) vs Mistral Large
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 31.9 on the Noometry Index.
Last verified . 42 shared benchmarks.
Google
Mistral AISummary
- They share 42 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 5 categories and Mistral Large in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 8.5% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Mistral Large | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 35.1 | 31.9 |
| Released | 2024-12-06 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 54 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Mistral Large: 34.3 (#240)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 45.9% | 30% |
| LiveBench Coding | 63.4% | 47.1% |
| LMArena Coding | 1350 | 1277 |
| BigCodeBench Complete | 59.9% | 38.3% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| SciCode | — | 36.2% |
| WeirdML | 25.8% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Too close to call
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Mistral Large: 28.6 (#89)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| TheAgentCompany | 11.4% | — |
Reasoning Too close to call
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Mistral Large: 15.8 (#310)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| SimpleBench | 31.1% | 22.5% |
| LiveBench Reasoning | 78.2% | 43.5% |
| LMArena Hard Prompts | 1346 | 1257 |
| DTBench | 63.2% | 65.1% |
| LiveBench Data Analysis | 69.4% | 50.1% |
| Epoch Capabilities Index | 135.36 | 128.52 |
| LiveBench | 66.9% | 48.4% |
| ARC-AGI-2 | 1.3% | — |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | — | 0% |
| EnigmaEval | 1.1% | — |
| LMCA | — | 16.7% |
| ForecastBench | — | 57.1 |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Mistral Large: 18.2 (#291)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 8.5% |
| Omni-MATH | 45.9% | 28.1% |
| LiveBench Math | 75.8% | 42.5% |
| LMArena Math | 1352 | 1262 |
| MATH Level 5 | 82.2% | 50.3% |
| FrontierMath (Feb 2025 set) | 1.7% | 0.3% |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Mistral Large: 30.1 (#230)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| GPQA Diamond | 64.1% | 51.3% |
| MMLU-Pro | 73.7% | 59.9% |
| Confabulations | 12.4% | 21.4% |
| GPQA (HELM) | 55.6% | 43.5% |
| LMArena Expert | 1339 | 1232 |
| MMLU | 79.7% | 80% |
| Humanity's Last Exam | 6.6% | — |
| Vectara Hallucination Rate | — | 4.5% |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Mistral Large: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Mistral Large: 40.0 (#219)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| LMArena Non-English | 1342 | 1237 |
| LMArena Chinese | 1373 | 1240 |
| LMArena French | 1391 | 1325 |
| LMArena German | 1353 | 1254 |
| LMArena Japanese | 1294 | 1188 |
| LMArena Korean | 1313 | 1202 |
| LMArena Russian | 1351 | 1257 |
| LMArena Spanish | 1363 | 1268 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Mistral Large: 67.9 (#191)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 67.9% |
| IFEval | 84.1% | 87.7% |
| LMArena Instruction Following | 1336 | 1249 |
Long Context Too close to call
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Mistral Large: 38.3 (#199)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1344 | 1261 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Mistral Large: 40.7 (#242)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Mistral Large |
|---|---|---|
| LMArena Text | 1354 | 1266 |
| LMArena Creative Writing | 1340 | 1243 |
| Short-Story Creative Writing | 73.8% | 69% |
| EQ-Bench Creative Writing | 1128 | 985 |
| WildBench | 80% | 80.1% |
| LMArena Multi-Turn | 1350 | 1260 |
| LiveBench Language | 51.3% | 39.4% |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Mistral Large?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 31.9 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Mistral Large share?
42 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Mistral Large has 51.