ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Haiku 3 vs Mixtral 8x7B vs Qwen2.5 7B Instruct

Claude Haiku 3 comes out ahead, 41 to 33 and 25 on our weighted score, though Qwen2.5 7B Instruct is 5.3× cheaper per token.

Price in rating: Excluded · Include price

Retired Mixtral 8x7B is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Our pick

    Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

    41/100
    • ECI117.8
    • Price$0.25 / $1.25
    • Context200K
  2. Mistral AI

    Mixtral 8x7B

    Released Dec 11, 2023Retired

    25/100
    • ECI118.5
    • Price$0.70 / $0.70
    • Context32K
  3. Alibaba (Qwen)

    Qwen2.5 7B Instruct

    Released Sep 19, 2024

    33/100
    • ECI—
    • Price$0.075 / $0.15
    • Context131K
01 — Verdict

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 Mixtral 8x7B (25). 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% · Mixtral 8x7B 30.6%
  • Lowest priceQwen2.5 7B InstructQwen2.5 7B Instruct $0.094 · Claude Haiku 3 $0.50 · Mixtral 8x7B $0.70 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Qwen2.5 7B Instruct 131,072 · Mixtral 8x7B 32,000 tokens
  • Widest inputsClaude Haiku 3Claude Haiku 3: Text, Images, PDFs · Mixtral 8x7B: Text · Qwen2.5 7B Instruct: Text
  • Self-hostingMixtral 8x7B and Qwen2.5 7B InstructPublishes downloadable weights (Apache 2.0)
How the score is built
MeasureWeightClaude Haiku 3Mixtral 8x7BQwen2.5 7B Instruct
CapabilityShared benchmarks67%363135
Inputs & features20%602525
Context window13%39032
Overall100%41/10025/10033/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Claude Haiku 3 vs Mixtral 8x7B vs Qwen2.5 7B Instruct specifications side by side
SpecificationClaude Haiku 3AnthropicMixtral 8x7BMistral AIQwen2.5 7B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)117.8118.5 (best)—
ECI rank#154 of 158#153 of 158 (best)—
GPQA DiamondGraduate-level science questions36.3% (best)30.6%35.5%
OTIS Mock AIME 2024–2025Competition mathematics1.8%—2.5% (best)
Price per million tokens
Input$0.25$0.70$0.075 (best)
Output$1.25$0.70$0.15 (best)
Cached input———
Blended (3:1)$0.50$0.70$0.094 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersOfficial Mistral APIMedian of 4 providers
Limits
Context window200,000 tokens (best)32,000 tokens131,072 tokens
Max output4,096 tokens32,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpenApache 2.0
API model ID—open-mixtral-8x7b—
API providers315 (best)
ReleasedMar 13, 2024Dec 11, 2023Sep 19, 2024
Knowledge cutoffAug 31, 2023Jan 2024—
03 — Cost

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
  • Mixtral 8x7B$8.40
  • Qwen2.5 7B Instruct$1.05
04 — Questions

Which should you choose?

Which is better: Claude Haiku 3, Mixtral 8x7B or Qwen2.5 7B Instruct?

Claude Haiku 3 is the better all-round choice, scoring 41/100 against Qwen2.5 7B Instruct (33) and Mixtral 8x7B (25). 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, Mixtral 8x7B 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). Claude Haiku 3 costs $0.25 input / $1.25 output per million tokens (median across 3 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 $0.094 per million tokens for Qwen2.5 7B Instruct versus $0.50 for Claude Haiku 3 (5.3× as much) and $0.70 for Mixtral 8x7B (7.5× 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 Mixtral 8x7B 30.6%. On individual benchmarks: GPQA Diamond — Claude Haiku 3 36.3%, Qwen2.5 7B Instruct 35.5%, Mixtral 8x7B 30.6%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 3, Mixtral 8x7B 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 32,000 for Mixtral 8x7B. Maximum output per response: Claude Haiku 3 up to 4,096, Mixtral 8x7B up to 32,000, 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; Mixtral 8x7B accepts text; Qwen2.5 7B Instruct accepts text. Claude Haiku 3 handles the widest range of inputs.

Are any of these open source?

Mixtral 8x7B 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. Claude Haiku 3 came out Mar 13, 2024; Mixtral 8x7B came out Dec 11, 2023. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Mixtral 8x7B Jan 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.