Model comparison
Mistral Nemo vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 31.4 to 26.4 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Mistral Nemo scores higher in 2 categories and Qwen-14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 31.2 to 25.5.
Side by side
| Mistral Nemo | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.4 | 31.4 |
| Released | 2024-07-01 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 10 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Qwen-14B: 31.2 (#288)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| LMArena Coding | — | 1071 |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), Qwen-14B: —
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Mistral Nemo leads
Mistral Nemo: 20.7 (#232), Qwen-14B: 19.6 (#257)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 118.68 | 113.03 |
| PIQA | 83.5% | 79.9% |
| LMArena Hard Prompts | — | 1027 |
| DTBench | 48.6% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
Math Qwen-14B leads
Mistral Nemo: 25.5 (#268), Qwen-14B: 31.2 (#227)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| GSM8K | 84.2% | 61.3% |
| LMArena Math | — | 1068 |
| MATH Level 5 | 10.8% | — |
Knowledge Not comparable
Mistral Nemo: 12.3 (#298), Qwen-14B: —
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| BoolQ | 82.5% | 86.2% |
| GPQA Diamond | 29.9% | — |
| ARC (AI2) Challenge | — | 84.4% |
| MMLU | — | 66.3% |
Multilingual Not comparable
Mistral Nemo: —, Qwen-14B: 27.5 (#275)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Mistral Nemo: —, Qwen-14B: 52.4 (#289)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Mistral Nemo: —, Qwen-14B: 31.3 (#280)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Too close to call
Mistral Nemo: 28.5 (#296), Qwen-14B: 27.6 (#299)
| Benchmark | Mistral Nemo | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| EQ-Bench Creative Writing | 881 | — |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Mistral Nemo better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 31.4 to 26.4 on the Noometry Index.
How many benchmarks do Mistral Nemo and Qwen-14B share?
4 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen-14B has 18.