Llama-3.1-70B-Instruct vs Mistral Large 2.1 vs Qwen2.5 32B Instruct
Too close to call on our weighted score (Mistral Large 2.1 29, Qwen2.5 32B Instruct 26, Llama-3.1-70B-Instruct 25). The right pick depends on what you value most.
Price in rating: Excluded · Include price
Retired Qwen2.5 32B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.
Meta
Llama-3.1-70B-Instruct
25/100- ECI124.7
- Price$0.72 / $0.72
- Context128K
Mistral AI
Mistral Large 2.1
29/100- ECI—
- Price$2.00 / $6.00
- Context131K
Alibaba (Qwen)
Qwen2.5 32B Instruct
26/100- ECI128.5
- Price$0.70 / $2.80
- Context131K
Too close to call
It is close. Our weighted score puts them within 3 points (Mistral Large 2.1 29/100, Qwen2.5 32B Instruct 26/100, Llama-3.1-70B-Instruct 25/100), so choose by what matters most for your work: Mistral Large 2.1 for raw capability and Llama-3.1-70B-Instruct on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Large 2.1 has no Capabilities Index score yet.
- CapabilityMistral Large 2.1Shared benchmarks: Mistral Large 2.1 29.6% · Qwen2.5 32B Instruct 26.7% · Llama-3.1-70B-Instruct 23.9%
- Lowest priceLlama-3.1-70B-InstructLlama-3.1-70B-Instruct $0.72 · Qwen2.5 32B Instruct $1.23 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend)
- Longest contextMistral Large 2.1 and Qwen2.5 32B InstructMistral Large 2.1 131,072 · Qwen2.5 32B Instruct 131,072 · Llama-3.1-70B-Instruct 128,000 tokens
- Widest inputsSame inputsLlama-3.1-70B-Instruct: Text · Mistral Large 2.1: Text · Qwen2.5 32B Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Llama-3.1-70B-Instruct | Mistral Large 2.1 | Qwen2.5 32B Instruct |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 24 | 30 | 27 |
| Inputs & features | 20% | 25 | 25 | 25 |
| Context window | 13% | 32 | 32 | 24 |
| Overall | 100% | 25/100 | 29/100 | 26/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 124.7 | — | 128.5 (best) |
| ECI rank | #146 of 158 | — | #138 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 44.2% | 51.3% (best) | 46.1% |
| OTIS Mock AIME 2024–2025Competition mathematics | 3.6% | 7.8% (best) | 7.4% |
| Price per million tokens | |||
| Input | $0.72 | $2.00 | $0.70 (best) |
| Output | $0.72 (best) | $6.00 | $2.80 |
| Cached input | — | — | — |
| Blended (3:1) | $0.72 (best) | $3.00 | $1.23 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 7 providers | Median of 2 providers | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Max output | 4,096 tokens | 16,384 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | 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 | — | — | qwen2-5-32b-instruct |
| API providers | 7 (best) | 2 | 1 |
| Released | Jul 23, 2024 | Nov 18, 2024 | Sep 17, 2024 |
| Knowledge cutoff | Dec 2023 | Nov 2024 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Llama-3.1-70B-Instruct$8.64
Mistral Large 2.1$32.00
Qwen2.5 32B Instruct$12.60
Which should you choose?
Which is better: Llama-3.1-70B-Instruct, Mistral Large 2.1 or Qwen2.5 32B Instruct?
It is close. Our weighted score puts them within 3 points (Mistral Large 2.1 29/100, Qwen2.5 32B Instruct 26/100, Llama-3.1-70B-Instruct 25/100), so choose by what matters most for your work: Mistral Large 2.1 for raw capability and Llama-3.1-70B-Instruct on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Large 2.1 has no Capabilities Index score yet.
Which is cheaper, Llama-3.1-70B-Instruct, Mistral Large 2.1 or Qwen2.5 32B Instruct?
Llama-3.1-70B-Instruct is cheaper at $0.72 input / $0.72 output per million tokens (median across 7 API providers). Qwen2.5 32B Instruct costs $0.70 input / $2.80 output per million tokens (official Alibaba API price); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.72 per million tokens for Llama-3.1-70B-Instruct versus $1.23 for Qwen2.5 32B Instruct (1.7× as much) and $3.00 for Mistral Large 2.1 (4.2× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Mistral Large 2.1 29.6%, Qwen2.5 32B Instruct 26.7% and Llama-3.1-70B-Instruct 23.9%. On individual benchmarks: GPQA Diamond — Mistral Large 2.1 51.3%, Qwen2.5 32B Instruct 46.1%, Llama-3.1-70B-Instruct 44.2%; OTIS Mock AIME 2024–2025 — Mistral Large 2.1 7.8%, Qwen2.5 32B Instruct 7.4%, Llama-3.1-70B-Instruct 3.6%.
Which is better for coding?
There are no published SWE-bench Verified results for Llama-3.1-70B-Instruct, Mistral Large 2.1 and Qwen2.5 32B Instruct yet, so there is no like-for-like coding score. On overall capability, Mistral Large 2.1 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Mistral Large 2.1 and Qwen2.5 32B Instruct have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Llama-3.1-70B-Instruct. Maximum output per response: Llama-3.1-70B-Instruct up to 4,096, Mistral Large 2.1 up to 16,384, Qwen2.5 32B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Llama-3.1-70B-Instruct accepts text; Mistral Large 2.1 accepts text; Qwen2.5 32B Instruct accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Mistral Large 2.1 is the newest, released Nov 18, 2024. Qwen2.5 32B Instruct came out Sep 17, 2024; Llama-3.1-70B-Instruct came out Jul 23, 2024. Knowledge cutoff: Llama-3.1-70B-Instruct Dec 2023, Mistral Large 2.1 Nov 2024, Qwen2.5 32B Instruct Apr 2024.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 Nov 18, 2026.