Claude Haiku 3 vs Mistral Nemo vs Qwen2.5 7B Instruct
Claude Haiku 3 comes out ahead, 41 to 33 and 29 on our weighted score, though Qwen2.5 7B Instruct is 5.3× cheaper per token.
Price in rating: Excluded · Include price
- Our pick
Anthropic
Claude Haiku 3
41/100- ECI117.8
- Price$0.25 / $1.25
- Context200K
Mistral AI
Mistral Nemo
29/100- ECI113.8
- Price$0.09 / $0.109
- Context128K
Alibaba (Qwen)
Qwen2.5 7B Instruct
33/100- ECI—
- Price$0.075 / $0.15
- Context131K
Claude Haiku 3 is our pick
Claude Haiku 3 is the better all-round choice, scoring 41/100 against Qwen2.5 7B Instruct (33) and Mistral Nemo (29). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because Qwen2.5 7B Instruct has no Capabilities Index score yet.
- CapabilityClaude Haiku 3Shared benchmarks: Claude Haiku 3 36.3% · Qwen2.5 7B Instruct 35.5% · Mistral Nemo 29.9%
- Lowest priceQwen2.5 7B InstructQwen2.5 7B Instruct $0.094 · Mistral Nemo $0.095 · Claude Haiku 3 $0.50 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Qwen2.5 7B Instruct 131,072 · Mistral Nemo 128,000 tokens
- Widest inputsClaude Haiku 3Claude Haiku 3: Text, Images, PDFs · Mistral Nemo: Text · Qwen2.5 7B Instruct: Text
- Self-hostingMistral Nemo and Qwen2.5 7B InstructPublishes downloadable weights (Apache 2.0)
| Measure | Weight | Claude Haiku 3 | Mistral Nemo | Qwen2.5 7B Instruct |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 36 | 30 | 35 |
| Inputs & features | 20% | 60 | 25 | 25 |
| Context window | 13% | 39 | 32 | 32 |
| Overall | 100% | 41/100 | 29/100 | 33/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 117.8 (best) | 113.8 | — |
| ECI rank | #154 of 158 (best) | #155 of 158 | — |
| GPQA DiamondGraduate-level science questions | 36.3% (best) | 29.9% | 35.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 1.8% | — | 2.5% (best) |
| Price per million tokens | |||
| Input | $0.25 | $0.09 | $0.075 (best) |
| Output | $1.25 | $0.109 (best) | $0.15 |
| Cached input | — | — | — |
| Blended (3:1) | $0.50 | $0.095 | $0.094 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 11 providers | Median of 4 providers |
| Limits | |||
| Context window | 200,000 tokens (best) | 128,000 tokens | 131,072 tokens |
| Max output | 4,096 tokens | 128,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | 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 | Proprietary | Open | OpenApache 2.0 |
| API model ID | — | — | — |
| API providers | 3 | 11 (best) | 5 |
| Released | Mar 13, 2024 | Jul 18, 2024 | Sep 19, 2024 |
| Knowledge cutoff | Aug 31, 2023 | Jul 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Claude Haiku 3$5.00
Mistral Nemo$1.12
Qwen2.5 7B Instruct$1.05
Which should you choose?
Which is better: Claude Haiku 3, Mistral Nemo or Qwen2.5 7B Instruct?
Claude Haiku 3 is the better all-round choice, scoring 41/100 against Qwen2.5 7B Instruct (33) and Mistral Nemo (29). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because Qwen2.5 7B Instruct has no Capabilities Index score yet.
Which is cheaper, Claude Haiku 3, Mistral Nemo or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper at $0.075 input / $0.15 output per million tokens (median across 4 API providers). Mistral Nemo costs $0.09 input / $0.109 output per million tokens (median across 11 API providers); Claude Haiku 3 costs $0.25 input / $1.25 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $0.094 per million tokens for Qwen2.5 7B Instruct versus $0.095 for Mistral Nemo (1× as much) and $0.50 for Claude Haiku 3 (5.3× 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): Claude Haiku 3 36.3%, Qwen2.5 7B Instruct 35.5% and Mistral Nemo 29.9%. On individual benchmarks: GPQA Diamond — Claude Haiku 3 36.3%, Qwen2.5 7B Instruct 35.5%, Mistral Nemo 29.9%.
Which is better for coding?
There are no published SWE-bench Verified results for Claude Haiku 3, Mistral Nemo and Qwen2.5 7B Instruct yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 3 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?
Claude Haiku 3 has the largest context window at 200,000 tokens, against 131,072 for Qwen2.5 7B Instruct and 128,000 for Mistral Nemo. Maximum output per response: Claude Haiku 3 up to 4,096, Mistral Nemo up to 128,000, Qwen2.5 7B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Claude Haiku 3 accepts text, images and PDFs; Mistral Nemo accepts text; Qwen2.5 7B Instruct accepts text. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
Mistral Nemo and Qwen2.5 7B Instruct publishes its weights (Apache 2.0) and can be self-hosted; Claude Haiku 3 is proprietary.
Which is newer?
Qwen2.5 7B Instruct is the newest, released Sep 19, 2024. Mistral Nemo came out Jul 18, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Mistral Nemo Jul 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.