Model comparison
Gemini 1.5 Pro (May 2024) vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 32.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
Mistral AISummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 4 categories and Mistral Small in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Mistral Small leads 28.1 to 17.9.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 46.8% for Mistral Small.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 32.1 | 33.4 |
| Released | 2024-02-15 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 45 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Pro (May 2024): 34.2 (#241), Mistral Small: 34.0 (#247)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 36.1% |
| LMArena Coding | 1294 | 1362 |
| BigCodeBench Complete | 57.5% | 46.6% |
| SciCode | — | 26.5% |
| WeirdML | 22.2% | — |
| LiveBench Coding | — | 36.2% |
| CadEval | 34% | — |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Mistral Small leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Mistral Small: 28.1 (#93)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Mistral Small leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Mistral Small: 19.8 (#250)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1335 |
| DTBench | 59% | 70.9% |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| BIG-Bench Hard | 89.2% | — |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
| LiveBench | — | 44% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Mistral Small: 16.4 (#293)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 5.8% |
| LMArena Math | 1315 | 1341 |
| MATH Level 5 | 70.4% | 46.8% |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 39.9% |
Knowledge Mistral Small leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Mistral Small: 31.0 (#222)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| GPQA Diamond | 57.2% | 47.5% |
| LMArena Expert | 1279 | 1291 |
| MMLU | 86.9% | 68.7% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 53.4% | — |
Multimodal Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), Mistral Small: 33.5 (#96)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Vision | 1161 | 1142 |
| Video-MME | 75% | — |
Multilingual Too close to call
Gemini 1.5 Pro (May 2024): 45.3 (#174), Mistral Small: 45.5 (#169)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Non-English | 1312 | 1315 |
| LMArena Chinese | 1331 | 1340 |
| LMArena French | 1302 | 1337 |
| LMArena German | 1286 | 1340 |
| LMArena Japanese | 1292 | 1275 |
| LMArena Korean | 1298 | 1259 |
| LMArena Russian | 1320 | 1324 |
| LMArena Spanish | 1311 | 1346 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Mistral Small: 66.4 (#209)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1297 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 83.7% | — |
Long Context Too close to call
Gemini 1.5 Pro (May 2024): 39.8 (#169), Mistral Small: 40.4 (#156)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1308 | 1327 |
Writing & Preference Too close to call
Gemini 1.5 Pro (May 2024): 52.4 (#172), Mistral Small: 52.5 (#171)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mistral Small |
|---|---|---|
| LMArena Text | 1319 | 1338 |
| LMArena Creative Writing | 1333 | 1305 |
| LMArena Multi-Turn | 1296 | 1344 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Mistral Small better for coding?
They score almost the same on coding (34.2 vs 34.0); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Mistral Small share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Mistral Small has 39.