ZMIME
Comparison · 3 models · Updated Nov 18, 2026

o3 vs DeepSeek V4 Pro vs Gemini 2.5 Pro

Gemini 2.5 Pro comes out ahead, 64 to 59 and 59 on our weighted score, though DeepSeek V4 Pro is 41% cheaper per token.

Price in rating: Included · Exclude price

  1. OpenAI

    o3

    Released Apr 16, 2025

    59/100
    • ECI147.1
    • Price$2.00 / $8.00
    • Context200K
  2. DeepSeek

    DeepSeek V4 Pro

    Released Apr 24, 2026

    59/100
    • ECI150.2
    • Price$1.60 / $3.33
    • Context1M
  3. Our pick

    Google

    Gemini 2.5 Pro

    Released Jun 17, 2025

    64/100
    • ECI144.9
    • Price$1.25 / $10.00
    • Context1.05M
01 — Verdict

Gemini 2.5 Pro is our pick

Gemini 2.5 Pro is the better all-round choice, scoring 64/100 against o3 (59) and DeepSeek V4 Pro (59). It leads on inputs & features. DeepSeek V4 Pro wins on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek V4 ProCapabilities Index (ECI): DeepSeek V4 Pro 150.2 · o3 147.1 · Gemini 2.5 Pro 144.9
  • Lowest priceDeepSeek V4 ProDeepSeek V4 Pro $2.03 · Gemini 2.5 Pro $3.44 · o3 $3.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · DeepSeek V4 Pro 1,000,000 · o3 200,000 tokens
  • Widest inputsGemini 2.5 Proo3: Text, Images, PDFs · DeepSeek V4 Pro: Text · Gemini 2.5 Pro: Text, Images, PDFs, Audio, Video
  • Self-hostingDeepSeek V4 ProPublishes downloadable weights
How the score is built
MeasureWeighto3DeepSeek V4 ProGemini 2.5 Pro
CapabilityCapabilities Index (ECI)50%757773
Price25%233423
Inputs & features15%8035100
Context window10%396465
Overall100%59/10059/10064/100
02 — Side by side

Every spec in one table

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

o3 vs DeepSeek V4 Pro vs Gemini 2.5 Pro specifications side by side
Specificationo3OpenAIDeepSeek V4 ProDeepSeekGemini 2.5 ProGoogle
Capability
Capabilities Index (ECI)147.1150.2 (best)144.9
ECI rank#81 of 158#67 of 158 (best)#92 of 158
GPQA DiamondGraduate-level science questions81.8%90.9% (best)85.3%
FrontierMath Tiers 1–3Research-level mathematics33.3%45.3% (best)24.6%
OTIS Mock AIME 2024–2025Competition mathematics84.4%96.7% (best)84.7%
SWE-bench VerifiedFixing real GitHub issues62.3%77.6% (best)57.6%
SimpleQA VerifiedShort factual questions49.4% (best)47.0%—
Price per million tokens
Input$2.00$1.60$1.25 (best)
Output$8.00$3.33 (best)$10.00
Cached input$0.50—$0.125 (best)
Blended (3:1)$3.50$2.03 (best)$3.44
Long-context rateSame rateSame rateOver 200K: $2.50 / $15.00
Price sourceOfficial OpenAI APIMedian of 65 providersOfficial Google API
Limits
Context window200,000 tokens1,000,000 tokens1,048,576 tokens (best)
Max output100,000 tokens384,000 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioNoNoYes
VideoNoNoYes
ReasoningYeslow · medium · highYesYes
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsProprietaryOpenProprietary
API model IDo3—gemini-2.5-pro
API providers2367 (best)31
ReleasedApr 16, 2025Apr 24, 2026Jun 17, 2025
Knowledge cutoffMay 2024May 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.

  • o3$36.00
  • DeepSeek V4 Pro$22.66
  • Gemini 2.5 Pro$32.50
04 — Questions

Which should you choose?

Which is better: o3, DeepSeek V4 Pro or Gemini 2.5 Pro?

Gemini 2.5 Pro is the better all-round choice, scoring 64/100 against o3 (59) and DeepSeek V4 Pro (59). It leads on inputs & features. DeepSeek V4 Pro wins on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, o3, DeepSeek V4 Pro or Gemini 2.5 Pro?

DeepSeek V4 Pro is cheaper at $1.60 input / $3.33 output per million tokens (median across 65 API providers). Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price); o3 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $2.03 per million tokens for DeepSeek V4 Pro versus $3.44 for Gemini 2.5 Pro (1.7× as much) and $3.50 for o3 (1.7× as much).

Which scores higher on benchmarks?

DeepSeek V4 Pro scores higher on the Capabilities Index (ECI): DeepSeek V4 Pro 150.2 (#67 of 158), o3 147.1 (#81 of 158) and Gemini 2.5 Pro 144.9 (#92 of 158). The confidence ranges of the top two overlap (148.5–152.0 vs 145.6–148.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek V4 Pro 90.9%, Gemini 2.5 Pro 85.3%, o3 81.8%; FrontierMath Tiers 1–3 — DeepSeek V4 Pro 45.3%, o3 33.3%, Gemini 2.5 Pro 24.6%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 96.7%, Gemini 2.5 Pro 84.7%, o3 84.4%; SWE-bench Verified — DeepSeek V4 Pro 77.6%, o3 62.3%, Gemini 2.5 Pro 57.6%.

Which is better for coding?

DeepSeek V4 Pro resolves more real GitHub issues on SWE-bench Verified: DeepSeek V4 Pro 77.6%, o3 62.3% and Gemini 2.5 Pro 57.6%. 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 1,000,000 for DeepSeek V4 Pro and 200,000 for o3. Maximum output per response: o3 up to 100,000, DeepSeek V4 Pro up to 384,000, Gemini 2.5 Pro up to 65,536 tokens.

Which can read images, PDFs, audio or video?

o3 accepts text, images and PDFs; DeepSeek V4 Pro accepts text; 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?

DeepSeek V4 Pro publishes its weights and can be self-hosted; o3 and Gemini 2.5 Pro is proprietary.

Which is newer?

DeepSeek V4 Pro is the newest, released Apr 24, 2026. Gemini 2.5 Pro came out Jun 17, 2025; o3 came out Apr 16, 2025. Knowledge cutoff: o3 May 2024, DeepSeek V4 Pro May 2025, Gemini 2.5 Pro Jan 2025.

How do you decide the winner?

This rating uses 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 18, 2026.