ZMIME
Comparison · 3 models · Updated Oct 4, 2026

o4-mini vs Claude Haiku 4.5 vs Gemini 2.5 Pro

Gemini 2.5 Pro comes out ahead, 63 to 59 and 58 on our weighted score, though o4-mini is 44% cheaper per token.

  1. OpenAI

    o4-mini

    Released Apr 16, 2025Deprecated

    59/100
    • ECI145.6
    • Price$1.10 / $4.40
    • Context200K
    Full specs Remove o4-mini

  2. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    58/100
    • ECI142.4
    • Price$1.00 / $5.00
    • Context200K
    Full specs Remove Claude Haiku 4.5
  3. Our pick

    Google

    Gemini 2.5 Pro

    Released Jun 17, 2025

    63/100
    • ECI145.3
    • Price$1.25 / $10.00
    • Context1.05M
    Full specs Remove Gemini 2.5 Pro
01 — Verdict

Gemini 2.5 Pro is our pick

Gemini 2.5 Pro is the better all-round choice, scoring 63/100 against o4-mini (59) and Claude Haiku 4.5 (58). It leads on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • Capabilityo4-miniCapabilities Index (ECI): o4-mini 145.6 · Gemini 2.5 Pro 145.3 · Claude Haiku 4.5 142.4
  • Lowest priceo4-minio4-mini $1.93 · Claude Haiku 4.5 $2.00 · Gemini 2.5 Pro $3.44 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · o4-mini 200,000 · Claude Haiku 4.5 200,000 tokens
  • Widest inputsGemini 2.5 Proo4-mini: Text, Images · Claude Haiku 4.5: Text, Images, PDFs · Gemini 2.5 Pro: Text, Images, PDFs, Audio, Video
  • Self-hostingNo open weightsAll three are available only through APIs
How the score is built
MeasureWeighto4-miniClaude Haiku 4.5Gemini 2.5 Pro
CapabilityCapabilities Index (ECI)50%736972
Price25%363624
Inputs & features15%7080100
Context window10%323261
Overall100%59/10058/10063/100
02 — Side by side

Every spec in one table

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

o4-mini vs Claude Haiku 4.5 vs Gemini 2.5 Pro specifications side by side
Specificationo4-miniOpenAIClaude Haiku 4.5AnthropicGemini 2.5 ProGoogle
Capability
Capabilities Index (ECI)145.6 (best)142.4145.3
ECI rank#76 of 148 (best)#90 of 148#78 of 148
GPQA DiamondGraduate-level science questions79.6%71.2%85.3% (best)
FrontierMath Tiers 1–3Research-level mathematics36.1% (best)—24.6%
OTIS Mock AIME 2024–2025Competition mathematics81.7%66.7%84.7% (best)
SWE-bench VerifiedFixing real GitHub issues——57.6%
SimpleQA VerifiedShort factual questions19.6% (best)13.2%—
Price per million tokens
Input$1.10$1.00 (best)$1.25
Output$4.40 (best)$5.00$10.00
Cached input$0.275$0.10 (best)$0.125
Blended (3:1)$1.93 (best)$2.00$3.44
Long-context rateSame rateSame rateOver 200K: $2.50 / $15.00
Price sourceOfficial OpenAI APIOfficial Anthropic APIOfficial Google API
Limits
Context window200,000 tokens200,000 tokens1,048,576 tokens (best)
Max output100,000 tokens (best)64,000 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesYes
AudioNoNoYes
VideoNoNoYes
ReasoningYeslow · medium · highYesYes
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDo4-miniclaude-haiku-4-5gemini-2.5-pro
API providers1934 (best)22
ReleasedApr 16, 2025Oct 15, 2025Jun 17, 2025
Knowledge cutoffMay 2024Feb 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.

  • o4-mini$19.80
  • Claude Haiku 4.5$20.00
  • Gemini 2.5 Pro$32.50
04 — Questions

Which should you choose?

Which is better: o4-mini, Claude Haiku 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro is the better all-round choice, scoring 63/100 against o4-mini (59) and Claude Haiku 4.5 (58). It leads on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, o4-mini, Claude Haiku 4.5 or Gemini 2.5 Pro?

o4-mini is cheaper at $1.10 input / $4.40 output per million tokens (official OpenAI API price). Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price); Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $1.93 per million tokens for o4-mini versus $2.00 for Claude Haiku 4.5 (1× as much) and $3.44 for Gemini 2.5 Pro (1.8× as much).

Which scores higher on benchmarks?

o4-mini scores higher on the Capabilities Index (ECI): o4-mini 145.6 (#76 of 148), Gemini 2.5 Pro 145.3 (#78 of 148) and Claude Haiku 4.5 142.4 (#90 of 148). The confidence ranges of the top two overlap (143.0–147.4 vs 143.6–146.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 2.5 Pro 85.3%, o4-mini 79.6%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Gemini 2.5 Pro 84.7%, o4-mini 81.7%, Claude Haiku 4.5 66.7%.

Which is better for coding?

There are no published SWE-bench Verified results for o4-mini and Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, o4-mini 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?

Gemini 2.5 Pro has the largest context window at 1,048,576 tokens, against 200,000 for o4-mini and 200,000 for Claude Haiku 4.5. Maximum output per response: o4-mini up to 100,000, Claude Haiku 4.5 up to 64,000, Gemini 2.5 Pro up to 65,536 tokens.

Which can read images, PDFs, audio or video?

o4-mini accepts text and images; Claude Haiku 4.5 accepts text, images and PDFs; Gemini 2.5 Pro accepts text, images, PDFs, audio and video. Gemini 2.5 Pro handles the widest range of inputs.

Are any of these open source?

No. o4-mini, Claude Haiku 4.5 and Gemini 2.5 Pro are proprietary and only available through APIs and apps.

Which is newer?

Claude Haiku 4.5 is the newest, released Oct 15, 2025. Gemini 2.5 Pro came out Jun 17, 2025; o4-mini came out Apr 16, 2025. Knowledge cutoff: o4-mini May 2024, Claude Haiku 4.5 Feb 28, 2025, Gemini 2.5 Pro 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons