ZMIME
Comparison · 3 models · Updated Nov 18, 2026

o4-mini vs Jamba Large vs Gemini 2.5 Pro

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. OpenAI

    o4-mini

    Released Apr 16, 2025Deprecated

    46/100
    • ECI145.2
    • Price$1.10 / $4.40
    • Context200K
  2. AI21 Labs

    Jamba Large

    Released Jul 3, 2025

    31/100
    • ECI—
    • Price$2.00 / $8.00
    • Context256K
  3. Google

    Gemini 2.5 Pro

    Released Jun 17, 2025

    55/100
    • ECI144.9
    • Price$1.25 / $10.00
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Pro 55/100, o4-mini 46/100, Jamba Large 31/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceo4-minio4-mini $1.93 · Gemini 2.5 Pro $3.44 · Jamba Large $3.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · Jamba Large 256,000 · o4-mini 200,000 tokens
  • Widest inputsGemini 2.5 Proo4-mini: Text, Images · Jamba Large: Text · Gemini 2.5 Pro: Text, Images, PDFs, Audio, Video
  • Self-hostingJamba LargePublishes downloadable weights
How the score is built
MeasureWeighto4-miniJamba LargeGemini 2.5 Pro
Price50%352323
Inputs & features30%7035100
Context window20%394365
Specs & price only100%46/10031/10055/100

Left out because at least one model lacks the data: capability. 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.

o4-mini vs Jamba Large vs Gemini 2.5 Pro specifications side by side
Specificationo4-miniOpenAIJamba LargeAI21 LabsGemini 2.5 ProGoogle
Capability
Capabilities Index (ECI)145.2 (best)—144.9
ECI rank#91 of 158 (best)—#92 of 158
GPQA DiamondGraduate-level science questions79.6%—85.3% (best)
FrontierMath Tiers 1–3Research-level mathematics36.1% (best)—24.6%
OTIS Mock AIME 2024–2025Competition mathematics81.7%—84.7% (best)
SWE-bench VerifiedFixing real GitHub issues——57.6%
SimpleQA VerifiedShort factual questions19.6%——
Price per million tokens
Input$1.10 (best)$2.00$1.25
Output$4.40 (best)$8.00$10.00
Cached input$0.275—$0.125 (best)
Blended (3:1)$1.93 (best)$3.50$3.44
Long-context rateSame rateSame rateOver 200K: $2.50 / $15.00
Price sourceOfficial OpenAI APIOfficial AI21 Labs APIOfficial Google API
Limits
Context window200,000 tokens256,000 tokens1,048,576 tokens (best)
Max output100,000 tokens (best)4,096 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoYes
AudioNoNoYes
VideoNoNoYes
ReasoningYeslow · medium · highNoYes
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryOpenProprietary
API model IDo4-minijamba-largegemini-2.5-pro
API providers17131 (best)
ReleasedApr 16, 2025Jul 3, 2025Jun 17, 2025
Knowledge cutoffMay 2024Aug 22, 2024Jan 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
  • Jamba Large$36.00
  • Gemini 2.5 Pro$32.50
04 — Questions

Which should you choose?

Which is better: o4-mini, Jamba Large or Gemini 2.5 Pro?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Pro 55/100, o4-mini 46/100, Jamba Large 31/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, o4-mini, Jamba Large or Gemini 2.5 Pro?

o4-mini is cheaper at $1.10 input / $4.40 output per million tokens (official OpenAI API price). Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price); Jamba Large costs $2.00 input / $8.00 output per million tokens (official AI21 Labs 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 $3.44 for Gemini 2.5 Pro (1.8× as much) and $3.50 for Jamba Large (1.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. o4-mini has an ECI of 145.2, Jamba Large has not been scored yet and Gemini 2.5 Pro has an ECI of 144.9.

Which is better for coding?

There are no published SWE-bench Verified results for o4-mini and Jamba Large yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. 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 256,000 for Jamba Large and 200,000 for o4-mini. Maximum output per response: o4-mini up to 100,000, Jamba Large up to 4,096, Gemini 2.5 Pro up to 65,536 tokens.

Which can read images, PDFs, audio or video?

o4-mini accepts text and images; Jamba Large 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?

Jamba Large publishes its weights and can be self-hosted; o4-mini and Gemini 2.5 Pro is proprietary.

Which is newer?

Jamba Large is the newest, released Jul 3, 2025. Gemini 2.5 Pro came out Jun 17, 2025; o4-mini came out Apr 16, 2025. Knowledge cutoff: o4-mini May 2024, Jamba Large Aug 22, 2024, Gemini 2.5 Pro Jan 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.