Model comparison
Codestral vs Gemma 2B
Codestral and Gemma 2B score almost the same on the Noometry Index (30.6 vs 29.6), 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 1 category and Gemma 2B in 1 category; one gap is clear of the uncertainty.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Gemma 2B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 29.6 |
| 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 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Codestral: 27.3 (#321), Gemma 2B: 29.4 (#305)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| HumanEval+ | 73.8% | 20.7% |
| MBPP+ | 61.9% | 34.1% |
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1010 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
Reasoning Too close to call
Codestral: 19.8 (#251), Gemma 2B: 18.8 (#275)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 989 |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Not comparable
Codestral: —, Gemma 2B: 30.0 (#239)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| LMArena Math | — | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Codestral: —, Gemma 2B: —
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual Not comparable
Codestral: —, Gemma 2B: 23.0 (#294)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| LMArena Non-English | — | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following Not comparable
Codestral: —, Gemma 2B: 48.5 (#302)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | — | 970 |
Long Context Not comparable
Codestral: —, Gemma 2B: 29.9 (#291)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Not comparable
Codestral: —, Gemma 2B: 24.0 (#308)
| Benchmark | Codestral | Gemma 2B |
|---|---|---|
| LMArena Text | — | 1002 |
| LMArena Creative Writing | — | 987 |
| LMArena Multi-Turn | — | 945 |
Frequently asked questions
Is Codestral better than Gemma 2B?
Codestral and Gemma 2B score almost the same on the Noometry Index (30.6 vs 29.6), so choose on price, context window or the category you care about most.
Is Codestral or Gemma 2B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Gemma 2B share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemma 2B has 23.