Model comparison
Codestral vs Gemini 2.0 Pro
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
GoogleSummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Gemini 2.0 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 2.0 Pro leads 37.8 to 27.3.
- The biggest single-benchmark swing is Aider Polyglot: 11.1% for Codestral and 35.6% for Gemini 2.0 Pro.
Side by side
| Codestral | Gemini 2.0 Pro | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 39.1 |
| Released | 2024-05-29 | 2025-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Pro leads
Codestral: 27.3 (#321), Gemini 2.0 Pro: 37.8 (#187)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| Aider Polyglot | 11.1% | 35.6% |
| BigCodeBench Instruct | 41.8% | — |
| LiveBench Coding | — | 63.5% |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Gemini 2.0 Pro leads
Codestral: 19.8 (#251), Gemini 2.0 Pro: 22.3 (#198)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| EnigmaEval | — | 0.7% |
| LiveBench Reasoning | — | 60.1% |
| LiveBench Data Analysis | — | 68% |
| Epoch Capabilities Index | — | 135.06 |
| LiveBench | — | 65.1% |
Math Not comparable
Codestral: —, Gemini 2.0 Pro: 39.7 (#100)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Math | — | 71% |
| MATH Level 5 | — | 83.5% |
Knowledge Not comparable
Codestral: —, Gemini 2.0 Pro: 36.5 (#167)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Confabulations | — | 18.4% |
Instruction Following Not comparable
Codestral: —, Gemini 2.0 Pro: 75.5 (#59)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Instruction Following | — | 83.4% |
Long Context Not comparable
Codestral: —, Gemini 2.0 Pro: 29.2 (#292)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| Fiction.LiveBench | — | 41.7% |
Writing & Preference Not comparable
Codestral: —, Gemini 2.0 Pro: 52.7 (#165)
| Benchmark | Codestral | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Language | — | 44.9% |
Frequently asked questions
Is Codestral better than Gemini 2.0 Pro?
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 30.6 on the Noometry Index.
Is Codestral or Gemini 2.0 Pro better for coding?
Gemini 2.0 Pro scores higher on coding benchmarks: 37.8 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Gemini 2.0 Pro share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Gemini 2.0 Pro has 14.