Model comparison
Codestral vs Qwen2-72B
Codestral and Qwen2-72B 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
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Qwen2-72B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2-72B leads 23.2 to 19.8.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 30.0 |
| Released | 2024-05-29 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Codestral: 27.3 (#321), Qwen2-72B: 29.1 (#310)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 38.5% |
| BigCodeBench Complete | 52.5% | 54% |
| Aider Polyglot | 11.1% | — |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Codestral: 19.8 (#251), Qwen2-72B: 23.2 (#181)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Not comparable
Codestral: —, Qwen2-72B: 30.2 (#236)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Codestral: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Not comparable
Codestral: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Codestral: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Codestral: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Codestral: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Codestral | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Codestral better than Qwen2-72B?
Codestral and Qwen2-72B 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 Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 29.1 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Qwen2-72B share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen2-72B has 26.