Head to head
Mistral 7B vs Qwen2.5-7B
Mistral 7B from Mistral AI against Qwen2.5-7B from Alibaba Qwen — specification, price and every benchmark both makers have published, in one table.
Benchmarks
Qwen2.5-7B leads
Qwen2.5-7B wins 2 of the 2 benchmarks both models report, Mistral 7B wins 0, by a wide margin. The average gap across shared tests is 35.4 points.
Price
Mistral 7B is cheaper
On a 3:1 input-to-output mix, Mistral 7B costs $0.025 per million tokens against $0.031 for Qwen2.5-7B — about 1.2× less.
What actually differs
- Qwen2.5-7B takes 131K tokens of context against 33K — 4.0× more room for long documents or a large codebase.
Scorecard
Which is better at what
Maths, coding, reasoning and the rest — one line each, averaged over the benchmarks both models actually report.
| Category | Mistral 7B | Qwen2.5-7B | Better at this |
|---|---|---|---|
| ReasoningNeither model reports this | — | — | Not comparable |
| MathsNeither model reports this | — | — | Not comparable |
| CodingHumanEval | 40.2% | 84.8% | Qwen2.5-7B+44.6 |
| KnowledgeMMLU-Pro | 30.0% | 56.3% | Qwen2.5-7B+26.3 |
| MultimodalNeither model reports this | — | — | Not comparable |
| Instruction followingNeither model reports this | — | — | Not comparable |
| Human preferenceNeither model reports this | — | — | Not comparable |
| Categories wonOut of 2 comparable | 0 | 2 | Qwen2.5-7B |
Each category averages only the benchmarks every model here reports, so no one is credited for a test the other did not run. A category with no shared test is marked Not comparable rather than guessed at.
Side by side
Mistral 7B and Qwen2.5-7B, row by row
| Attribute | Mistral 7BMistral AI | Qwen2.5-7BAlibaba Qwen |
|---|---|---|
| Specification | ||
| MakerWho built it | Mistral AI | Alibaba Qwen |
| Released | 2023-09 | 2024-09 |
| ParametersTotal, and active per token for a mixture of experts | 7B | 7B |
| Architecture | Dense transformer | Dense transformer |
| Context windowHow much can go in at once | 32,768 tokens | 131,072 tokens |
| Max output | 8,192 tokens | 8,192 tokens |
| Input | Text | Text |
| ReasoningSpends extra tokens thinking before it answers | No | No |
| Tool calling | No | Yes |
| Licence | Apache 2.0 | Apache 2.0 |
| Open weightsCan you download and run it yourself | Yes | Yes |
| Price | ||
| Input priceUSD per million tokens in | $0.025 | $0.025 |
| Output priceUSD per million tokens out | $0.025 | $0.05 |
| Blended 3:1A 3-in-to-1-out million-token mix — a fairer single number than input price alone | $0.025Cheapest | $0.031 |
| Price note | Open weights — this is a representative hosting rate, not a first-party price. Running it yourself costs only hardware. | Open weights — this is a representative hosting rate, not a first-party price. Running it yourself costs only hardware. |
| Published benchmarks | ||
| MMLU-Pro12,000 reasoning-heavy multiple-choice questions across 14 academic subjects, with ten options instead of four. The harder successor to MMLU. | ||
| HumanEval164 short Python functions written from a docstring. Saturated at the frontier — kept here for continuity with older models. | ||
| Links | Hugging Face · Full page | Hugging Face · Full page |
| Row verified | 2026-08 | 2026-08 |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
Questions
Mistral 7B or Qwen2.5-7B?
Is Mistral 7B better than Qwen2.5-7B?
Qwen2.5-7B wins 2 of the 2 benchmarks both models report, Mistral 7B wins 0, by a wide margin. The average gap across shared tests is 35.4 points.
Which is cheaper, Mistral 7B or Qwen2.5-7B?
On a 3:1 input-to-output mix, Mistral 7B costs $0.025 per million tokens against $0.031 for Qwen2.5-7B — about 1.2× less.
What is the difference between Mistral 7B and Qwen2.5-7B?
Qwen2.5-7B takes 131K tokens of context against 33K — 4.0× more room for long documents or a large codebase.