ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen2.5 32B Instruct vs Claude Haiku 3.5 vs Mistral Large 2.1

Claude Haiku 3.5 comes out ahead, 49 to 42 and 42 on our weighted score.

  1. Alibaba (Qwen)

    Qwen2.5 32B Instruct

    Released Sep 17, 2024

    42/100
    • ECI128.5
    • Price$0.70 / $2.80
    • Context131K
    Full specs Remove Qwen2.5 32B Instruct
  2. Our pick

    Anthropic

    Claude Haiku 3.5

    Released Oct 22, 2024

    49/100
    • ECI127.2
    • Price—
    • Context200K
    Full specs Remove Claude Haiku 3.5

  3. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    42/100
    • ECI128.5
    • Price$2.00 / $6.00
    • Context131K
    Full specs Remove Mistral Large 2.1
01 — Verdict

Claude Haiku 3.5 is our pick

Claude Haiku 3.5 is the better all-round choice, scoring 49/100 against Qwen2.5 32B Instruct (42) and Mistral Large 2.1 (42). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityQwen2.5 32B Instruct and Mistral Large 2.1Capabilities Index (ECI): Qwen2.5 32B Instruct 128.5 · Mistral Large 2.1 128.5 · Claude Haiku 3.5 127.2
  • Lowest priceQwen2.5 32B InstructQwen2.5 32B Instruct $1.23 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend) · Claude Haiku 3.5 unpriced
  • Longest contextClaude Haiku 3.5Claude Haiku 3.5 200,000 · Qwen2.5 32B Instruct 131,072 · Mistral Large 2.1 131,072 tokens
  • Widest inputsClaude Haiku 3.5Qwen2.5 32B Instruct: Text · Claude Haiku 3.5: Text, Images, PDFs · Mistral Large 2.1: Text
  • Self-hostingQwen2.5 32B Instruct and Mistral Large 2.1Publishes downloadable weights
How the score is built
MeasureWeightQwen2.5 32B InstructClaude Haiku 3.5Mistral Large 2.1
CapabilityCapabilities Index (ECI)67%514951
Inputs & features20%256025
Context window13%243224
Overall100%42/10049/10042/100

Left out because at least one model lacks the data: price. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Qwen2.5 32B Instruct vs Claude Haiku 3.5 vs Mistral Large 2.1 specifications side by side
SpecificationQwen2.5 32B InstructAlibaba (Qwen)Claude Haiku 3.5AnthropicMistral Large 2.1Mistral AI
Capability
Capabilities Index (ECI)128.5 (best)127.2128.5 (best)
ECI rank#131 of 148#134 of 148#130 of 148 (best)
GPQA DiamondGraduate-level science questions46.1%38.1%51.3% (best)
OTIS Mock AIME 2024–2025Competition mathematics7.4%4.3%7.8% (best)
Price per million tokens
Input$0.70 (best)—$2.00
Output$2.80 (best)—$6.00
Cached input———
Blended (3:1)$1.23 (best)—$3.00
Long-context rateSame rate—Same rate
Price sourceOfficial Alibaba API—Official Mistral API
Limits
Context window131,072 tokens200,000 tokens (best)131,072 tokens
Max output8,192 tokens8,192 tokens16,384 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpen
API model IDqwen2-5-32b-instruct—mistral-large-2411
API providers1—2 (best)
ReleasedSep 17, 2024Oct 22, 2024Nov 18, 2024
Knowledge cutoffApr 2024Jul 31, 2024Nov 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.

  • Qwen2.5 32B Instruct$12.60
  • Claude Haiku 3.5—
  • Mistral Large 2.1$32.00
04 — Questions

Which should you choose?

Which is better: Qwen2.5 32B Instruct, Claude Haiku 3.5 or Mistral Large 2.1?

Claude Haiku 3.5 is the better all-round choice, scoring 49/100 against Qwen2.5 32B Instruct (42) and Mistral Large 2.1 (42). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Qwen2.5 32B Instruct, Claude Haiku 3.5 or Mistral Large 2.1?

Qwen2.5 32B Instruct is cheaper at $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 (official Mistral API price). At a typical mix of three input tokens to one output token, that is $1.23 per million tokens for Qwen2.5 32B Instruct versus $3.00 for Mistral Large 2.1 (2.4× as much). Claude Haiku 3.5 has no published per-token price.

Which scores higher on benchmarks?

Qwen2.5 32B Instruct scores higher on the Capabilities Index (ECI): Qwen2.5 32B Instruct 128.5 (#131 of 148), Mistral Large 2.1 128.5 (#130 of 148) and Claude Haiku 3.5 127.2 (#134 of 148). The confidence ranges of the top two overlap (123.5–130.0 vs 123.8–130.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — Mistral Large 2.1 51.3%, Qwen2.5 32B Instruct 46.1%, Claude Haiku 3.5 38.1%; OTIS Mock AIME 2024–2025 — Mistral Large 2.1 7.8%, Qwen2.5 32B Instruct 7.4%, Claude Haiku 3.5 4.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen2.5 32B Instruct, Claude Haiku 3.5 and Mistral Large 2.1 yet, so there is no like-for-like coding score. On overall capability, Qwen2.5 32B Instruct 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 3.5 has the largest context window at 200,000 tokens, against 131,072 for Qwen2.5 32B Instruct and 131,072 for Mistral Large 2.1. Maximum output per response: Qwen2.5 32B Instruct up to 8,192, Claude Haiku 3.5 up to 8,192, Mistral Large 2.1 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

Qwen2.5 32B Instruct accepts text; Claude Haiku 3.5 accepts text, images and PDFs; Mistral Large 2.1 accepts text. Claude Haiku 3.5 handles the widest range of inputs.

Are any of these open source?

Qwen2.5 32B Instruct and Mistral Large 2.1 publishes its weights and can be self-hosted; Claude Haiku 3.5 is proprietary.

Which is newer?

Mistral Large 2.1 is the newest, released Nov 18, 2024. Claude Haiku 3.5 came out Oct 22, 2024; Qwen2.5 32B Instruct came out Sep 17, 2024. Knowledge cutoff: Qwen2.5 32B Instruct Apr 2024, Claude Haiku 3.5 Jul 31, 2024, Mistral Large 2.1 Nov 2024.

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.

05 — Keep comparing

Related comparisons