Mistral Medium 3.5 vs QwQ 32B vs Claude Haiku 4.5
Claude Haiku 4.5 comes out ahead, 60 to 56 and 55 on our weighted score, though QwQ 32B is 3.5× cheaper per token.
Price in rating: Included · Exclude price
Mistral AI
Mistral Medium 3.5
56/100- ECI141.6
- Price$1.50 / $7.50
- Context262K
Alibaba (Qwen)
QwQ 32B
55/100- ECI136.5
- Price$0.53 / $0.70
- Context131K
- Our pick
Anthropic
Claude Haiku 4.5
60/100- ECI142.8
- Price$1.00 / $5.00
- Context200K
Claude Haiku 4.5 is our pick
Claude Haiku 4.5 is the better all-round choice, scoring 60/100 against Mistral Medium 3.5 (56) and QwQ 32B (55). It leads on inputs & features. Mistral Medium 3.5 wins on context window. QwQ 32B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Haiku 4.5Capabilities Index (ECI): Claude Haiku 4.5 142.8 · Mistral Medium 3.5 141.6 · QwQ 32B 136.5
- Lowest priceQwQ 32BQwQ 32B $0.573 · Claude Haiku 4.5 $2.00 · Mistral Medium 3.5 $3.00 per 1M tokens (3:1 blend)
- Longest contextMistral Medium 3.5Mistral Medium 3.5 262,144 · Claude Haiku 4.5 200,000 · QwQ 32B 131,072 tokens
- Widest inputsClaude Haiku 4.5Mistral Medium 3.5: Text, Images · QwQ 32B: Text · Claude Haiku 4.5: Text, Images, PDFs
- Self-hostingMistral Medium 3.5 and QwQ 32BPublishes downloadable weights
| Measure | Weight | Mistral Medium 3.5 | QwQ 32B | Claude Haiku 4.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 69 | 65 | 70 |
| Price | 25% | 26 | 59 | 34 |
| Inputs & features | 15% | 70 | 35 | 80 |
| Context window | 10% | 43 | 32 | 39 |
| Overall | 100% | 56/100 | 55/100 | 60/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.6 | 136.5 | 142.8 (best) |
| ECI rank | #107 of 158 | #122 of 158 | #102 of 158 (best) |
| GPQA DiamondGraduate-level science questions | — | 65.3% | 71.2% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 59.2% | 66.7% (best) |
| SimpleQA VerifiedShort factual questions | — | — | 13.2% |
| Price per million tokens | |||
| Input | $1.50 | $0.53 (best) | $1.00 |
| Output | $7.50 | $0.70 (best) | $5.00 |
| Cached input | $0.15 | — | $0.10 (best) |
| Blended (3:1) | $3.00 | $0.573 (best) | $2.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 2 providers | Official Anthropic API |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 200,000 tokens |
| Max output | 262,144 tokens (best) | 8,192 tokens | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeshigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | mistral-medium-2604 | — | claude-haiku-4-5 |
| API providers | 16 | 2 | 57 (best) |
| Released | Apr 29, 2026 | Mar 5, 2025 | Oct 15, 2025 |
| Knowledge cutoff | — | Apr 2024 | Feb 28, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Mistral Medium 3.5$30.00
QwQ 32B$6.70
Claude Haiku 4.5$20.00
Which should you choose?
Which is better: Mistral Medium 3.5, QwQ 32B or Claude Haiku 4.5?
Claude Haiku 4.5 is the better all-round choice, scoring 60/100 against Mistral Medium 3.5 (56) and QwQ 32B (55). It leads on inputs & features. Mistral Medium 3.5 wins on context window. QwQ 32B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Mistral Medium 3.5, QwQ 32B or Claude Haiku 4.5?
QwQ 32B is cheaper at $0.53 input / $0.70 output per million tokens (median across 2 API providers). Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price); Mistral Medium 3.5 costs $1.50 input / $7.50 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.573 per million tokens for QwQ 32B versus $2.00 for Claude Haiku 4.5 (3.5× as much) and $3.00 for Mistral Medium 3.5 (5.2× as much).
Which scores higher on benchmarks?
Claude Haiku 4.5 scores higher on the Capabilities Index (ECI): Claude Haiku 4.5 142.8 (#102 of 158), Mistral Medium 3.5 141.6 (#107 of 158) and QwQ 32B 136.5 (#122 of 158). The confidence ranges of the top two overlap (141.2–144.3 vs 138.4–144.7), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Medium 3.5, QwQ 32B and Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 4.5 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 Medium 3.5 has the largest context window at 262,144 tokens, against 200,000 for Claude Haiku 4.5 and 131,072 for QwQ 32B. Maximum output per response: Mistral Medium 3.5 up to 262,144, QwQ 32B up to 8,192, Claude Haiku 4.5 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
Mistral Medium 3.5 accepts text and images; QwQ 32B accepts text; Claude Haiku 4.5 accepts text, images and PDFs. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
Mistral Medium 3.5 and QwQ 32B publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.
Which is newer?
Mistral Medium 3.5 is the newest, released Apr 29, 2026. Claude Haiku 4.5 came out Oct 15, 2025; QwQ 32B came out Mar 5, 2025. Knowledge cutoff: QwQ 32B Apr 2024, Claude Haiku 4.5 Feb 28, 2025.
How do you decide the winner?
This rating uses 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 Nov 18, 2026.