Model comparison
Gemini 1.5 Pro (May 2024) vs Mixtral 8x22B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.1 on the Noometry Index.
Last verified . 34 shared benchmarks.
Google
Mistral AISummary
- They share 34 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 7 categories and Mixtral 8x22B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 36.9.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 24.2% for Mixtral 8x22B.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Mixtral 8x22B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 32.1 | 27.1 |
| Released | 2024-02-15 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 45 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| WeirdML | 22.2% | 3.2% |
| BigCodeBench Instruct | 43.8% | 40.6% |
| LMArena Coding | 1294 | 1166 |
| BigCodeBench Complete | 57.5% | 50.2% |
| HumanEval+ | 79.3% | 72% |
| MBPP+ | 74.6% | 64.3% |
| CadEval | 34% | — |
Agentic & Tool Use Mixtral 8x22B leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Mixtral 8x22B: 23.1 (#127)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| Cybench | 7.5% | 7.5% |
| TheAgentCompany | 3.4% | — |
| BALROG | 21% | — |
Reasoning Mixtral 8x22B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1150 |
| DTBench | 59% | 55.1% |
| Epoch Capabilities Index | 131.73 | 122.03 |
| ForecastBench | 58.4 | 56.3 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| BIG-Bench Hard | 89.2% | — |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 36.4% | 16.3% |
| LMArena Math | 1315 | 1184 |
| MATH Level 5 | 70.4% | 24.2% |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 57.2% | 34.1% |
| MMLU-Pro | 73.7% | 46% |
| GPQA (HELM) | 53.4% | 33.4% |
| LMArena Expert | 1279 | 1113 |
| MMLU | 86.9% | 77.8% |
| Humanity's Last Exam | 4.6% | — |
| Confabulations | 13.5% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Mixtral 8x22B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1312 | 1128 |
| LMArena Chinese | 1331 | 1116 |
| LMArena French | 1302 | 1166 |
| LMArena German | 1286 | 1141 |
| LMArena Japanese | 1292 | 1037 |
| LMArena Korean | 1298 | 1057 |
| LMArena Russian | 1320 | 1158 |
| LMArena Spanish | 1311 | 1151 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| IFEval | 83.7% | 72.4% |
| LMArena Instruction Following | 1297 | 1147 |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1308 | 1144 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Gemini 1.5 Pro (May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1319 | 1162 |
| LMArena Creative Writing | 1333 | 1141 |
| WildBench | 81.3% | 71.1% |
| LMArena Multi-Turn | 1296 | 1130 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Mixtral 8x22B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Mixtral 8x22B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 24.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Mixtral 8x22B share?
34 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Mixtral 8x22B has 34.