Qwen2.5 72B Instruct vs Mistral Large 3 vs Mistral Large 2.1
Mistral Large 3 comes out ahead, 50 to 28 and 26 on our weighted score, and it is the cheaper option too.
Alibaba (Qwen)Qwen2.5 72B Instruct
28/100- ECI129.0
- Price$1.40 / $5.60
- Context131K
- Our pick
Mistral AIMistral Large 3
50/100- ECI—
- Price$0.50 / $1.50
- Context262K
- Mistral AI
Mistral Large 2.1
26/100- ECI128.5
- Price$2.00 / $6.00
- Context131K
Mistral Large 3 is our pick
Mistral Large 3 is the better all-round choice, scoring 50/100 against Qwen2.5 72B Instruct (28) and Mistral Large 2.1 (26). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceMistral Large 3Mistral Large 3 $0.75 · Qwen2.5 72B Instruct $2.45 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend)
- Longest contextMistral Large 3Mistral Large 3 262,144 · Qwen2.5 72B Instruct 131,072 · Mistral Large 2.1 131,072 tokens
- Widest inputsMistral Large 3Qwen2.5 72B Instruct: Text · Mistral Large 3: Text, Images · Mistral Large 2.1: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Qwen2.5 72B Instruct | Mistral Large 3 | Mistral Large 2.1 |
|---|---|---|---|---|
| Price | 50% | 31 | 56 | 27 |
| Inputs & features | 30% | 25 | 50 | 25 |
| Context window | 20% | 24 | 37 | 24 |
| Overall | 100% | 28/100 | 50/100 | 26/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen2.5 72B InstructAlibaba (Qwen) | Mistral Large 3Mistral AI | Mistral Large 2.1Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 129.0 (best) | — | 128.5 |
| ECI rank | #128 of 148 (best) | — | #130 of 148 |
| GPQA DiamondGraduate-level science questions | 49.2% | — | 51.3% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 8.1% (best) | — | 7.8% |
| Price per million tokens | |||
| Input | $1.40 | $0.50 (best) | $2.00 |
| Output | $5.60 | $1.50 (best) | $6.00 |
| Cached input | — | $0.05 | — |
| Blended (3:1) | $2.45 | $0.75 (best) | $3.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Mistral API | Official Mistral API |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 131,072 tokens |
| Max output | 8,192 tokens | 262,144 tokens (best) | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | qwen2-5-72b-instruct | mistral-large-2512 | mistral-large-2411 |
| API providers | 1 | 13 (best) | 2 |
| Released | Sep 19, 2024 | Dec 2, 2025 | Nov 18, 2024 |
| Knowledge cutoff | Apr 2024 | Nov 2024 | Nov 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen2.5 72B Instruct$25.20
- Mistral Large 3$8.00
- Mistral Large 2.1$32.00
Which should you choose?
Which is better: Qwen2.5 72B Instruct, Mistral Large 3 or Mistral Large 2.1?
Mistral Large 3 is the better all-round choice, scoring 50/100 against Qwen2.5 72B Instruct (28) and Mistral Large 2.1 (26). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Qwen2.5 72B Instruct, Mistral Large 3 or Mistral Large 2.1?
Mistral Large 3 is cheaper at $0.50 input / $1.50 output per million tokens (official Mistral API price). Qwen2.5 72B Instruct costs $1.40 input / $5.60 output per million tokens (official Alibaba API price); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.75 per million tokens for Mistral Large 3 versus $2.45 for Qwen2.5 72B Instruct (3.3× as much) and $3.00 for Mistral Large 2.1 (4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen2.5 72B Instruct has an ECI of 129.0, Mistral Large 3 has not been scored yet and Mistral Large 2.1 has an ECI of 128.5.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen2.5 72B Instruct, Mistral Large 3 and Mistral Large 2.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Mistral Large 3 has the largest context window at 262,144 tokens, against 131,072 for Qwen2.5 72B Instruct and 131,072 for Mistral Large 2.1. Maximum output per response: Qwen2.5 72B Instruct up to 8,192, Mistral Large 3 up to 262,144, Mistral Large 2.1 up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Qwen2.5 72B Instruct accepts text; Mistral Large 3 accepts text and images; Mistral Large 2.1 accepts text. Mistral Large 3 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Mistral Large 3 is the newest, released Dec 2, 2025. Mistral Large 2.1 came out Nov 18, 2024; Qwen2.5 72B Instruct came out Sep 19, 2024. Knowledge cutoff: Qwen2.5 72B Instruct Apr 2024, Mistral Large 3 Nov 2024, Mistral Large 2.1 Nov 2024.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
