Model comparison
Codestral vs Qwen1.5-72B
Codestral and Qwen1.5-72B score almost the same on the Noometry Index (30.1 vs 30.3), so choose on price, context window or the category you care about most.
Last verified . 4 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Codestral scores higher in 0 categories and Qwen1.5-72B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen1.5-72B leads 31.4 to 26.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 40.3% for Qwen1.5-72B.
Side by side
| Codestral | Qwen1.5-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 30.3 |
| Released | 2024-05-29 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-72B leads
Codestral: 26.9 (#316), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 33.2% |
| BigCodeBench Complete | 52.5% | 40.3% |
| HumanEval+ | 73.8% | 59.1% |
| MBPP+ | 61.9% | 61.6% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1166 |
| ALE-Bench | 137.78 | — |
Reasoning Qwen1.5-72B leads
Codestral: 19.1 (#244), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1148 |
Math Not comparable
Codestral: —, Qwen1.5-72B: 30.7 (#205)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |
Knowledge Not comparable
Codestral: —, Qwen1.5-72B: 11.5 (#295)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
Multilingual Not comparable
Codestral: —, Qwen1.5-72B: 33.4 (#248)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1158 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
Codestral: —, Qwen1.5-72B: 59.6 (#251)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1142 |
Long Context Not comparable
Codestral: —, Qwen1.5-72B: 35.0 (#238)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
Codestral: —, Qwen1.5-72B: 37.4 (#253)
| Benchmark | Codestral | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is Codestral better than Qwen1.5-72B?
Codestral and Qwen1.5-72B score almost the same on the Noometry Index (30.1 vs 30.3), so choose on price, context window or the category you care about most.
Is Codestral or Qwen1.5-72B better for coding?
Qwen1.5-72B scores higher on coding benchmarks: 31.4 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Qwen1.5-72B share?
4 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen1.5-72B has 22.