Model comparison
Mistral Nemo vs Qwen2.5-VL 72B Instruct
Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index. Mistral Nemo costs 28× less per token, which makes it the better buy when Qwen2.5-VL 72B Instruct's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in agentic & tool use, where Mistral Nemo leads 23.3 to 18.4.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Qwen2.5-VL 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Mistral Nemo | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 25.9 | 29.4 |
| Released | 2024-07-01 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.15 | $2.80 |
| Output $ / M tokens | $0.15 | $8.40 |
| Results tracked | 10 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Agentic & Tool Use Mistral Nemo leads
Mistral Nemo: 23.3 (#118), Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| OSWorld | — | 5% |
| BALROG | 17.6% | — |
Reasoning Too close to call
Mistral Nemo: 19.9 (#230), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| DTBench | 48.6% | — |
| Epoch Capabilities Index | 118.63 | — |
| PIQA | 83.5% | — |
Math Not comparable
Mistral Nemo: 23.5 (#263), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| MATH Level 5 | 10.8% | — |
| GSM8K | 84.2% | — |
Knowledge Not comparable
Mistral Nemo: 12.3 (#293), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| GPQA Diamond | 29.9% | — |
| BoolQ | 82.5% | — |
Multimodal Not comparable
Mistral Nemo: —, Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Writing & Preference Not comparable
Mistral Nemo: 28.6 (#291), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Nemo | Qwen2.5-VL 72B Instruct |
|---|---|---|
| EQ-Bench Creative Writing | 881 | — |
Frequently asked questions
Is Mistral Nemo better than Qwen2.5-VL 72B Instruct?
Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index. Mistral Nemo costs 28× less per token, which makes it the better buy when Qwen2.5-VL 72B Instruct's lead doesn't matter for your workload.
Which is cheaper, Mistral Nemo or Qwen2.5-VL 72B Instruct?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Qwen2.5-VL 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Mistral Nemo and Qwen2.5-VL 72B Instruct share?
0 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.