Model comparison
Mistral Nemo vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 26.4 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Mistral Nemo scores higher in 1 category and Qwen2-72B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 28.5.
- The biggest single-benchmark swing is MATH Level 5: 10.8% for Mistral Nemo and 39.1% for Qwen2-72B.
Side by side
| Mistral Nemo | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.4 | 30.0 |
| Released | 2024-07-01 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 10 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Qwen2-72B: 29.1 (#310)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Mistral Nemo leads
Mistral Nemo: 23.5 (#125), Qwen2-72B: 17.0 (#146)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| TheAgentCompany | — | 1.1% |
| BALROG | 17.6% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Mistral Nemo: 20.7 (#232), Qwen2-72B: 23.2 (#181)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 118.68 | 125.28 |
| LMArena Hard Prompts | — | 1191 |
| DTBench | 48.6% | — |
| PIQA | 83.5% | — |
Math Qwen2-72B leads
Mistral Nemo: 25.5 (#268), Qwen2-72B: 30.2 (#236)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| MATH Level 5 | 10.8% | 39.1% |
| LMArena Math | — | 1235 |
| GSM8K | 84.2% | — |
Knowledge Qwen2-72B leads
Mistral Nemo: 12.3 (#298), Qwen2-72B: 21.2 (#275)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 29.9% | 40.8% |
| LMArena Expert | — | 1171 |
| BoolQ | 82.5% | — |
| MMLU | — | 82.4% |
Multilingual Not comparable
Mistral Nemo: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Mistral Nemo | 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
Mistral Nemo: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Mistral Nemo: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Qwen2-72B leads
Mistral Nemo: 28.5 (#296), Qwen2-72B: 40.8 (#241)
| Benchmark | Mistral Nemo | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| EQ-Bench Creative Writing | 881 | — |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Mistral Nemo better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 26.4 on the Noometry Index.
How many benchmarks do Mistral Nemo and Qwen2-72B share?
3 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen2-72B has 26.