Model comparison
Codestral vs Dolly 2.0-12b
Codestral is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
DatabricksSummary
- The widest gap is in reasoning, where Codestral leads 19.8 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Codestral | Dolly 2.0-12b | |
|---|---|---|
| Provider | Mistral AI | Databricks |
| Noometry Index | 30.6 | 25.5 |
| Released | 2024-05-29 | 2023-04-11 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codestral leads
Codestral: 27.3 (#321), Dolly 2.0-12b: 23.4 (#332)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 776 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Codestral leads
Codestral: 19.8 (#251), Dolly 2.0-12b: 15.3 (#316)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 804 |
| Epoch Capabilities Index | — | 89.67 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math Not comparable
Codestral: —, Dolly 2.0-12b: 27.3 (#251)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | — | 871 |
Knowledge Not comparable
Codestral: —, Dolly 2.0-12b: —
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual Not comparable
Codestral: —, Dolly 2.0-12b: 17.4 (#296)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | — | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Not comparable
Codestral: —, Dolly 2.0-12b: 38.7 (#304)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | — | 814 |
Writing & Preference Not comparable
Codestral: —, Dolly 2.0-12b: 15.2 (#311)
| Benchmark | Codestral | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | — | 851 |
| LMArena Creative Writing | — | 864 |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is Codestral better than Dolly 2.0-12b?
Codestral is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Is Codestral or Dolly 2.0-12b better for coding?
Codestral scores higher on coding benchmarks: 27.3 versus 23.4 in the Noometry coding category.
How many benchmarks do Codestral and Dolly 2.0-12b share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Dolly 2.0-12b has 17.