Model comparison
Codestral vs Gemma 2 9B
Codestral is the stronger model overall, scoring 30.1 to 25.7 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 Gemma 2 9B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.1 to 15.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 40.6% for Gemma 2 9B.
Side by side
| Codestral | Gemma 2 9B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.1 | 25.7 |
| Released | 2024-05-29 | 2024-06-24 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Codestral: 26.9 (#316), Gemma 2 9B: 29.0 (#299)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 34.7% |
| BigCodeBench Complete | 52.5% | 40.6% |
| Aider Polyglot | 11.1% | — |
| LiveBench Coding | — | 22.5% |
| LMArena Coding | — | 1174 |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Codestral leads
Codestral: 19.1 (#244), Gemma 2 9B: 15.3 (#306)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LiveBench Reasoning | — | 15.2% |
| LMArena Hard Prompts | — | 1172 |
| LiveBench Data Analysis | — | 36.4% |
| Epoch Capabilities Index | — | 119.78 |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Not comparable
Codestral: —, Gemma 2 9B: 9.3 (#312)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| LiveBench Math | — | 19.8% |
| LMArena Math | — | 1183 |
| MATH Level 5 | — | 21% |
| GSM8K | — | 84.9% |
Knowledge Not comparable
Codestral: —, Gemma 2 9B: 9.7 (#300)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | — | 27.5% |
| LMArena Expert | — | 1147 |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |
Multilingual Not comparable
Codestral: —, Gemma 2 9B: 36.8 (#233)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | — | 1188 |
| LMArena Chinese | — | 1185 |
| LMArena French | — | 1189 |
| LMArena German | — | 1186 |
| LMArena Japanese | — | 1144 |
| LMArena Korean | — | 1137 |
| LMArena Russian | — | 1200 |
| LMArena Spanish | — | 1200 |
Instruction Following Not comparable
Codestral: —, Gemma 2 9B: 57.8 (#264)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | — | 52.6% |
| LMArena Instruction Following | — | 1178 |
Long Context Not comparable
Codestral: —, Gemma 2 9B: 36.3 (#228)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | — | 1197 |
Writing & Preference Not comparable
Codestral: —, Gemma 2 9B: 32.3 (#276)
| Benchmark | Codestral | Gemma 2 9B |
|---|---|---|
| LMArena Text | — | 1207 |
| LMArena Creative Writing | — | 1206 |
| EQ-Bench Creative Writing | — | 841 |
| LMArena Multi-Turn | — | 1193 |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Codestral better than Gemma 2 9B?
Codestral is the stronger model overall, scoring 30.1 to 25.7 on the Noometry Index.
Is Codestral or Gemma 2 9B better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.0 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Gemma 2 9B share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemma 2 9B has 35.