ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Phi-4-mini vs GPT-4o vs Reka Flash 3

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

  1. Microsoft

    Phi-4-mini

    Released Feb 26, 2025

    72/100
    • ECI—
    • Price$0.075 / $0.30
    • Context128K
  2. OpenAI

    GPT-4o

    Released May 13, 2024

    22/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  3. Reka AI

    Reka Flash 3

    Released Mar 10, 2025

    69/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
  4. Microsoft

    Phi-4-mini

    Released Feb 26, 2025

    32/100
    • ECI—
    • Price$0.075 / $0.30
    • Context128K
  5. OpenAI

    GPT-4o

    Released May 13, 2024

    32/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  6. Reka AI

    Reka Flash 3

    Released Mar 10, 2025

    22/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-mini 72/100, Reka Flash 3 69/100, GPT-4o 22/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-mini 32/100, GPT-4o 32/100, Reka Flash 3 22/100) compare the available specifications only. The score weighs context window 100%. 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 priceReka Flash 3Reka Flash 3 $0.125 · Phi-4-mini $0.131 · GPT-4o $4.38 per 1M tokens (3:1 blend)
  • Longest contextPhi-4-mini and GPT-4oPhi-4-mini 128,000 · GPT-4o 128,000 · Reka Flash 3 65,536 tokens
  • Widest inputsGPT-4oPhi-4-mini: Text · GPT-4o: Text, Images, PDFs · Reka Flash 3: Text
  • Self-hostingPhi-4-mini and Reka Flash 3Publishes downloadable weights
How the score is built
MeasureWeightPhi-4-miniGPT-4oReka Flash 3
Price71%881989
Context window29%323222
Specs & price only100%72/10022/10069/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightPhi-4-miniGPT-4oReka Flash 3
Context window100%323222
Specs only100%32/10032/10022/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Phi-4-mini vs GPT-4o vs Reka Flash 3 specifications side by side
SpecificationPhi-4-miniMicrosoftGPT-4oOpenAIReka Flash 3Reka AI
Capability
Capabilities Index (ECI)Not published128.1Not published
ECI rankNot published#140 of 159Not published
ECI confidence intervalNot published125.4–130.7Not published
ECI evaluation dateNot publishedMay 13, 2024Not published
Documented capabilitiesCompact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasksOmni-era GPT for multimodal chat, practical coding, and general assistantsEfficient model for low-latency assistance, extraction, and routine automation
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questionsNot published48.9%Not published
OTIS Mock AIME 2024–2025Competition mathematicsNot published6.3%Not published
Publisher-reported benchmarks
MMLUPublisher-reported result67.3accuracyReported resultNot publishedNot published
Aider PolyglotPublisher-reported resultNot published23.1percent correctReported resultDec 30, 2024Not published
Price per million tokens
Input$0.075 (best)$2.50$0.10
Output$0.30$10.00$0.20 (best)
Cached inputNot published$1.25Not published
Blended (3:1)$0.131$4.38$0.125 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Azure APIOfficial OpenAI APIMedian of 3 providers
Limits
Context window128,000 tokens (best)128,000 tokens (best)65,536 tokens
Max inputNot publishedNot publishedNot published
Max output4,096 tokens16,384 tokens58,982 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesNo
Structured outputNot publishedYesNot published
File attachmentsNoYesNo
Temperature controlYesYesYes
Reasoning controlNot publishedNot publishedalways
Availability
WeightsOpenProprietaryOpen
API model IDphi-4-minigpt-4oNot published
API providers227 (best)3
ReleasedFeb 26, 2025May 13, 2024Mar 10, 2025
Knowledge cutoffJun 2024Sep 2023Jan 31, 2025
Publisher documentationPublisher documentation · Model weightsPublisher documentationModel weights
Source metadata updatedFeb 26, 2025Aug 6, 2024Mar 10, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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.

  • Phi-4-mini$1.35
  • GPT-4o$45.00
  • Reka Flash 3$1.40
04 — Questions

Which should you choose?

Which is better: Phi-4-mini, GPT-4o or Reka Flash 3?

There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-mini 72/100, Reka Flash 3 69/100, GPT-4o 22/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-mini 32/100, GPT-4o 32/100, Reka Flash 3 22/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Phi-4-mini, GPT-4o or Reka Flash 3?

Reka Flash 3 is cheaper at $0.10 input / $0.20 output per million tokens (median across 3 API providers). Phi-4-mini costs $0.075 input / $0.30 output per million tokens (official Azure API price); GPT-4o costs $2.50 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.125 per million tokens for Reka Flash 3 versus $0.131 for Phi-4-mini (1× as much) and $4.38 for GPT-4o (35× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Phi-4-mini has not been scored yet, GPT-4o has an ECI of 128.1 and Reka Flash 3 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Phi-4-mini, GPT-4o and Reka Flash 3 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Reka Flash 3 has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

Phi-4-mini and GPT-4o have the largest context windows (128,000 and 128,000 tokens), against 65,536 for Reka Flash 3. Maximum output per response: Phi-4-mini up to 4,096, GPT-4o up to 16,384, Reka Flash 3 up to 58,982 tokens.

Which can read images, PDFs, audio or video?

Phi-4-mini accepts text; GPT-4o accepts text, images and PDFs; Reka Flash 3 accepts text. GPT-4o handles the widest range of inputs.

Are any of these open source?

Phi-4-mini and Reka Flash 3 publishes its weights and can be self-hosted; GPT-4o is proprietary.

Which is newer?

Reka Flash 3 is the newest, released Mar 10, 2025. Phi-4-mini came out Feb 26, 2025; GPT-4o came out May 13, 2024. Knowledge cutoff: Phi-4-mini Jun 2024, GPT-4o Sep 2023, Reka Flash 3 Jan 31, 2025.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.