Model comparison
Codestral vs Gemini 1.0 Pro
Codestral is the stronger model overall, scoring 30.6 to 27.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
GoogleSummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 1 category and Gemini 1.0 Pro in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 1.0 Pro leads 32.2 to 27.3.
Side by side
| Codestral | Gemini 1.0 Pro | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 27.3 |
| Released | 2024-05-29 | 2023-12-13 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Codestral: 27.3 (#321), Gemini 1.0 Pro: 32.2 (#275)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| HumanEval+ | 73.8% | 55.5% |
| MBPP+ | 61.9% | 61.4% |
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1108 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
Reasoning Codestral leads
Codestral: 19.8 (#251), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1109 |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 117.04 |
Math Not comparable
Codestral: —, Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LMArena Math | — | 1132 |
| MATH Level 5 | — | 11.2% |
Knowledge Not comparable
Codestral: —, Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | — | 34% |
| LMArena Expert | — | 1059 |
| MMLU | — | 70% |
Multilingual Not comparable
Codestral: —, Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | — | 1138 |
| LMArena Chinese | — | 1124 |
| LMArena French | — | 1145 |
| LMArena German | — | 1125 |
| LMArena Japanese | — | 1023 |
| LMArena Russian | — | 1186 |
| LMArena Spanish | — | 1119 |
Instruction Following Not comparable
Codestral: —, Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | — | 1114 |
Long Context Not comparable
Codestral: —, Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | — | 1132 |
Writing & Preference Not comparable
Codestral: —, Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | Codestral | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | — | 1149 |
| LMArena Creative Writing | — | 1131 |
| LMArena Multi-Turn | — | 1139 |
Frequently asked questions
Is Codestral better than Gemini 1.0 Pro?
Codestral is the stronger model overall, scoring 30.6 to 27.3 on the Noometry Index.
Is Codestral or Gemini 1.0 Pro better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Gemini 1.0 Pro share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemini 1.0 Pro has 24.