Model comparison
Codestral vs Gemma 7B
Codestral and Gemma 7B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 2 shared benchmarks.
Mistral AI
GoogleSummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Gemma 7B in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Gemma 7B leads 30.5 to 27.3.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Gemma 7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 30.0 |
| Released | 2024-05-29 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Codestral: 27.3 (#321), Gemma 7B: 30.5 (#294)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| HumanEval+ | 73.8% | 28.7% |
| MBPP+ | 61.9% | 43.4% |
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1048 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
Reasoning Too close to call
Codestral: 19.8 (#251), Gemma 7B: 19.9 (#249)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1042 |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| Epoch Capabilities Index | — | 111.99 |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Not comparable
Codestral: —, Gemma 7B: 31.2 (#228)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Math | — | 1066 |
| GSM8K | — | 46.4% |
Knowledge Not comparable
Codestral: —, Gemma 7B: 27.3 (#252)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Expert | — | 1001 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual Not comparable
Codestral: —, Gemma 7B: 25.1 (#287)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Non-English | — | 999 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |
Instruction Following Not comparable
Codestral: —, Gemma 7B: 51.5 (#295)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | — | 1017 |
Long Context Not comparable
Codestral: —, Gemma 7B: 31.1 (#282)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |
Writing & Preference Not comparable
Codestral: —, Gemma 7B: 27.1 (#302)
| Benchmark | Codestral | Gemma 7B |
|---|---|---|
| LMArena Text | — | 1056 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 963 |
Frequently asked questions
Is Codestral better than Gemma 7B?
Codestral and Gemma 7B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Is Codestral or Gemma 7B better for coding?
Gemma 7B scores higher on coding benchmarks: 30.5 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Gemma 7B share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemma 7B has 27.