Model comparison
Codestral vs Gemini 1.5 Pro (May 2024)
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.6 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AI
GoogleSummary
- They share 4 benchmarks with published results for both. Codestral scores higher in 1 category and Gemini 1.5 Pro (May 2024) in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.8 to 12.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 57.5% for Gemini 1.5 Pro (May 2024).
Side by side
| Codestral | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 32.1 |
| Released | 2024-05-29 | 2024-02-15 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Codestral: 27.3 (#321), Gemini 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 43.8% |
| BigCodeBench Complete | 52.5% | 57.5% |
| HumanEval+ | 73.8% | 79.3% |
| MBPP+ | 61.9% | 74.6% |
| Aider Polyglot | 11.1% | — |
| WeirdML | — | 22.2% |
| LMArena Coding | — | 1294 |
| CadEval | — | 34% |
| ALE-Bench | 137.78 | — |
Agentic & Tool Use Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
Reasoning Codestral leads
Codestral: 19.8 (#251), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 27.1% |
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1296 |
| DTBench | — | 59% |
| BIG-Bench Hard | — | 89.2% |
| Epoch Capabilities Index | — | 131.73 |
| ForecastBench | — | 58.4 |
Math Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 23.1% |
| Omni-MATH | — | 36.4% |
| LMArena Math | — | 1315 |
| MATH Level 5 | — | 70.4% |
Knowledge Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | — | 57.2% |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| GPQA (HELM) | — | 53.4% |
| LMArena Expert | — | 1279 |
| MMLU | — | 86.9% |
Multimodal Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
Multilingual Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | — | 1312 |
| LMArena Chinese | — | 1331 |
| LMArena French | — | 1302 |
| LMArena German | — | 1286 |
| LMArena Japanese | — | 1292 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1320 |
| LMArena Spanish | — | 1311 |
Instruction Following Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| IFEval | — | 83.7% |
| LMArena Instruction Following | — | 1297 |
Long Context Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | — | 1308 |
Writing & Preference Not comparable
Codestral: —, Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | Codestral | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | — | 1319 |
| LMArena Creative Writing | — | 1333 |
| WildBench | — | 81.3% |
| LMArena Multi-Turn | — | 1296 |
Frequently asked questions
Is Codestral better than Gemini 1.5 Pro (May 2024)?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.6 on the Noometry Index.
Is Codestral or Gemini 1.5 Pro (May 2024) better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Gemini 1.5 Pro (May 2024) share?
4 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.