Mixtral 8x7B vs Ministral 8B Instruct vs Claude Haiku 3
Claude Haiku 3 comes out ahead, 46 to 42 and 33 on our weighted score, though Ministral 8B Instruct is 3.3× cheaper per token.
Mistral AIMixtral 8x7B
33/100- ECI118.5
- Price$0.70 / $0.70
- Context32K
- Mistral AI
Ministral 8B Instruct
42/100- ECI—
- Price$0.15 / $0.15
- Context131K
- Our pick
AnthropicClaude Haiku 3
46/100- ECI118.4
- Price$0.25 / $1.25
- Context200K
Claude Haiku 3 is our pick
Claude Haiku 3 is the better all-round choice, scoring 46/100 against Ministral 8B Instruct (42) and Mixtral 8x7B (33). It leads on capability, inputs & features and context window. Ministral 8B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because Ministral 8B Instruct has no Capabilities Index score yet.
- CapabilityClaude Haiku 3Shared benchmarks: Claude Haiku 3 36.3% · Mixtral 8x7B 30.6% · Ministral 8B Instruct 27.2%
- Lowest priceMinistral 8B InstructMinistral 8B Instruct $0.15 · Claude Haiku 3 $0.50 · Mixtral 8x7B $0.70 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Ministral 8B Instruct 131,072 · Mixtral 8x7B 32,000 tokens
- Widest inputsClaude Haiku 3Mixtral 8x7B: Text · Ministral 8B Instruct: Text · Claude Haiku 3: Text, Images, PDFs
- Self-hostingMixtral 8x7B and Ministral 8B InstructPublishes downloadable weights (Mistral Research License)
| Measure | Weight | Mixtral 8x7B | Ministral 8B Instruct | Claude Haiku 3 |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 31 | 27 | 36 |
| Price | 25% | 57 | 89 | 64 |
| Inputs & features | 15% | 25 | 25 | 60 |
| Context window | 10% | 0 | 24 | 32 |
| Overall | 100% | 33/100 | 42/100 | 46/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Mixtral 8x7BMistral AI | Ministral 8B InstructMistral AI | Claude Haiku 3Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 118.5 (best) | — | 118.4 |
| ECI rank | #142 of 148 (best) | — | #143 of 148 |
| GPQA DiamondGraduate-level science questions | 30.6% | 27.2% | 36.3% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 1.8% |
| Price per million tokens | |||
| Input | $0.70 | $0.15 (best) | $0.25 |
| Output | $0.70 | $0.15 (best) | $1.25 |
| Cached input | — | — | — |
| Blended (3:1) | $0.70 | $0.15 (best) | $0.50 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 1 providers | Median of 2 providers |
| Limits | |||
| Context window | 32,000 tokens | 131,072 tokens | 200,000 tokens (best) |
| Max output | 32,000 tokens (best) | 8,192 tokens | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| 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 | OpenMistral Research License | Proprietary |
| API model ID | open-mixtral-8x7b | — | — |
| API providers | 1 | 1 | 2 (best) |
| Released | Dec 11, 2023 | Oct 16, 2024 | Mar 13, 2024 |
| Knowledge cutoff | Jan 2024 | — | Aug 31, 2023 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mixtral 8x7B$8.40
- Ministral 8B Instruct$1.80
- Claude Haiku 3$5.00
Which should you choose?
Which is better: Mixtral 8x7B, Ministral 8B Instruct or Claude Haiku 3?
Claude Haiku 3 is the better all-round choice, scoring 46/100 against Ministral 8B Instruct (42) and Mixtral 8x7B (33). It leads on capability, inputs & features and context window. Ministral 8B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because Ministral 8B Instruct has no Capabilities Index score yet.
Which is cheaper, Mixtral 8x7B, Ministral 8B Instruct or Claude Haiku 3?
Ministral 8B Instruct is cheaper at $0.15 input / $0.15 output per million tokens (median across 1 API provider). Claude Haiku 3 costs $0.25 input / $1.25 output per million tokens (median across 2 API providers); Mixtral 8x7B costs $0.70 input / $0.70 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 8B Instruct versus $0.50 for Claude Haiku 3 (3.3× as much) and $0.70 for Mixtral 8x7B (4.7× 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%, Mixtral 8x7B 30.6% and Ministral 8B Instruct 27.2%. On individual benchmarks: GPQA Diamond — Claude Haiku 3 36.3%, Mixtral 8x7B 30.6%, Ministral 8B Instruct 27.2%.
Which is better for coding?
There are no published SWE-bench Verified results for Mixtral 8x7B, Ministral 8B Instruct and Claude Haiku 3 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 Ministral 8B Instruct and 32,000 for Mixtral 8x7B. Maximum output per response: Mixtral 8x7B up to 32,000, Ministral 8B Instruct up to 8,192, Claude Haiku 3 up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Mixtral 8x7B accepts text; Ministral 8B Instruct accepts text; Claude Haiku 3 accepts text, images and PDFs. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
Mixtral 8x7B and Ministral 8B Instruct publishes its weights (Mistral Research License) and can be self-hosted; Claude Haiku 3 is proprietary.
Which is newer?
Ministral 8B Instruct is the newest, released Oct 16, 2024. Claude Haiku 3 came out Mar 13, 2024; Mixtral 8x7B came out Dec 11, 2023. Knowledge cutoff: Mixtral 8x7B Jan 2024, Claude Haiku 3 Aug 31, 2023.
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.
Related comparisons
- Mixtral 8x7B vs Qwen2.5 7B InstructAlibaba (Qwen) · ECI 118.5
- Mixtral 8x7B vs Llama-3.1-70B-InstructMeta · ECI 125.9
- Mixtral 8x7B vs Nova ProAmazon · ECI 123.8
- Ministral 8B Instruct vs Llama-3.1-8B-InstructMeta · ECI 116.6
- Ministral 8B Instruct vs Gemma 3 4B ITGoogle · ECI 116.1
- Ministral 8B Instruct vs Qwen2.5 7B InstructAlibaba (Qwen) · ECI 118.5
