ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Qwen3.5 Flash vs Claude Haiku 4.5 vs Gemma 4 31B IT

Qwen3.5 Flash comes out ahead, 73 to 68 and 57 on our weighted score, and it is the cheaper option too.

  1. Our pick

    Alibaba (Qwen)

    Qwen3.5 Flash

    Released Feb 23, 2026

    73/100
    • ECI143.6
    • Price$0.10 / $0.40
    • Context1M
    Full specs Remove Qwen3.5 Flash

  2. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    57/100
    • ECI142.2
    • Price$1.00 / $5.00
    • Context200K
    Full specs Remove Claude Haiku 4.5

  3. Google

    Gemma 4 31B IT

    Released Apr 2, 2026

    68/100
    • ECI143.1
    • Price$0.14 / $0.40
    • Context262K
    Full specs Remove Gemma 4 31B IT
01 — Verdict

Qwen3.5 Flash is our pick

Qwen3.5 Flash is the better all-round choice, scoring 73/100 against Gemma 4 31B IT (68) and Claude Haiku 4.5 (57). It leads on price and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.5 FlashCapabilities Index (ECI): Qwen3.5 Flash 143.6 · Gemma 4 31B IT 143.1 · Claude Haiku 4.5 142.2
  • Lowest priceQwen3.5 FlashQwen3.5 Flash $0.175 · Gemma 4 31B IT $0.205 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
  • Longest contextQwen3.5 FlashQwen3.5 Flash 1,000,000 · Gemma 4 31B IT 262,144 · Claude Haiku 4.5 200,000 tokens
  • Widest inputsQwen3.5 Flash and Claude Haiku 4.5Qwen3.5 Flash: Text, Images, Video · Claude Haiku 4.5: Text, Images, PDFs · Gemma 4 31B IT: Text, Images
  • Self-hostingGemma 4 31B ITPublishes downloadable weights
How the score is built
MeasureWeightQwen3.5 FlashClaude Haiku 4.5Gemma 4 31B IT
CapabilityCapabilities Index (ECI)50%696768
Price25%823479
Inputs & features15%808070
Context window10%603237
Overall100%73/10057/10068/100
02 — Side by side

Every spec in one table

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

Qwen3.5 Flash vs Claude Haiku 4.5 vs Gemma 4 31B IT specifications side by side
SpecificationQwen3.5 FlashAlibaba (Qwen)Claude Haiku 4.5AnthropicGemma 4 31B ITGoogle
Capability
Capabilities Index (ECI)143.6 (best)142.2143.1
ECI rank#95 of 165 (best)#102 of 165#96 of 165
GPQA DiamondGraduate-level science questions82.3% (best)71.2%75.8%
FrontierMath Tiers 1–3Research-level mathematics18.3%——
OTIS Mock AIME 2024–2025Competition mathematics84.4% (best)66.7%73.3%
SimpleQA VerifiedShort factual questions20.3% (best)13.2%10.4%
Price per million tokens
Input$0.10 (best)$1.00$0.14
Output$0.40 (best)$5.00$0.40 (best)
Cached input$0.01 (best)$0.10—
Blended (3:1)$0.175 (best)$2.00$0.205
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Anthropic APIMedian of 36 providers
Limits
Context window1,000,000 tokens (best)200,000 tokens262,144 tokens
Max output65,536 tokens (best)64,000 tokens32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoNo
VideoYesNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryProprietaryOpen
API model IDqwen3.5-flashclaude-haiku-4-5gemma-4-31b-it
API providers948 (best)46
ReleasedFeb 23, 2026Oct 15, 2025Apr 2, 2026
Knowledge cutoff—Feb 28, 2025Jan 2025
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.

  • Qwen3.5 Flash$1.80
  • Claude Haiku 4.5$20.00
  • Gemma 4 31B IT$2.20
04 — Questions

Which should you choose?

Which is better: Qwen3.5 Flash, Claude Haiku 4.5 or Gemma 4 31B IT?

Qwen3.5 Flash is the better all-round choice, scoring 73/100 against Gemma 4 31B IT (68) and Claude Haiku 4.5 (57). It leads on price and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3.5 Flash, Claude Haiku 4.5 or Gemma 4 31B IT?

Qwen3.5 Flash is cheaper at $0.10 input / $0.40 output per million tokens (official Alibaba API price). Gemma 4 31B IT costs $0.14 input / $0.40 output per million tokens (median across 36 API providers); Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for Qwen3.5 Flash versus $0.205 for Gemma 4 31B IT (1.2× as much) and $2.00 for Claude Haiku 4.5 (11× as much).

Which scores higher on benchmarks?

Qwen3.5 Flash scores higher on the Capabilities Index (ECI): Qwen3.5 Flash 143.6 (#95 of 165), Gemma 4 31B IT 143.1 (#96 of 165) and Claude Haiku 4.5 142.2 (#102 of 165). The confidence ranges of the top two overlap (141.4–145.0 vs 140.8–145.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.5 Flash 82.3%, Gemma 4 31B IT 75.8%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Qwen3.5 Flash 84.4%, Gemma 4 31B IT 73.3%, Claude Haiku 4.5 66.7%; SimpleQA Verified — Qwen3.5 Flash 20.3%, Claude Haiku 4.5 13.2%, Gemma 4 31B IT 10.4%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.5 Flash, Claude Haiku 4.5 and Gemma 4 31B IT yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 Flash 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?

Qwen3.5 Flash has the largest context window at 1,000,000 tokens, against 262,144 for Gemma 4 31B IT and 200,000 for Claude Haiku 4.5. Maximum output per response: Qwen3.5 Flash up to 65,536, Claude Haiku 4.5 up to 64,000, Gemma 4 31B IT up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Qwen3.5 Flash accepts text, images and video; Claude Haiku 4.5 accepts text, images and PDFs; Gemma 4 31B IT accepts text and images. Qwen3.5 Flash handles the widest range of inputs.

Are any of these open source?

Gemma 4 31B IT publishes its weights and can be self-hosted; Qwen3.5 Flash and Claude Haiku 4.5 is proprietary.

Which is newer?

Gemma 4 31B IT is the newest, released Apr 2, 2026. Qwen3.5 Flash came out Feb 23, 2026; Claude Haiku 4.5 came out Oct 15, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, Gemma 4 31B IT Jan 2025.

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons