All models
Microsoft·2025-02-26·4 evaluations

Phi-4 Multimodal

Phi-4 Multimodal Instruct

Open weightsMIT

Intelligence

5.81

#480 of 520 models

Output speed

17.2 tok/s

Measured generation rate

Cost / index task

—

Measured evaluation workload

End-to-end latency

30ms

First answer 1ms

01 / Position

A model in the landscape

Compare this model with peers across intelligence, speed, cost, and individual evaluations.

Model comparison
Intelligence vs. Time per task
Explore the trade-off: intelligence on the vertical axis, with peers colored by developer.
Selected · Phi-4 Multimodal26 models plottedBest trade-offs shaded
Most attractive regionLeast attractive regionPareto frontierAnthropicOpenAIMeta
1.1 min4.8 min8.4 min12.1 min15.7 min46.249.352.355.458.5Time per task (minutes)Intelligence IndexClaude Opus 5.5 (max with fallback) · Anthropic Time per task: 13.4 min Intelligence Index: 57.6Claude Opus 5.5 (xhigh with fallback) · Anthropic Time per task: 8.4 min Intelligence Index: 56.0Claude Sonnet 5.5 (max with fallback) · Anthropic Time per task: 14.5 min Intelligence Index: 56.0Claude Opus 5.5 (high with fallback) · Anthropic Time per task: 4.9 min Intelligence Index: 53.6Claude Fable 5.1 (max with fallback) · Anthropic Time per task: 12.1 min Intelligence Index: 53.4Claude Fable 5.1 (xhigh with fallback) · Anthropic Time per task: 11.3 min Intelligence Index: 53.2GPT-6 Astra (max) · OpenAI Time per task: 7.8 min Intelligence Index: 52.8GPT-6 Astra (xhigh) · OpenAI Time per task: 5.5 min Intelligence Index: 52.5Claude Sonnet 5.5 (xhigh with fallback) · Anthropic Time per task: 7.4 min Intelligence Index: 51.9GPT-6.1 Sol (max) · OpenAI Time per task: 9.5 min Intelligence Index: 51.8Claude Opus 5.5 (medium with fallback) · Anthropic Time per task: 3.6 min Intelligence Index: 51.2Claude Fable 5.1 (high with fallback) · Anthropic Time per task: 7.4 min Intelligence Index: 51.2GPT-6 Astra (high) · OpenAI Time per task: 4.0 min Intelligence Index: 51.0GPT-6.1 Sol (xhigh) · OpenAI Time per task: 4.5 min Intelligence Index: 51.0Claude Opus 5 (max) · Anthropic Time per task: 14.7 min Intelligence Index: 50.7GPT-6.1 Sol (high) · OpenAI Time per task: 3.4 min Intelligence Index: 50.2Claude Fable 5 (with fallback) · Anthropic Time per task: 11.4 min Intelligence Index: 49.7GPT-6 Astra (medium) · OpenAI Time per task: 3.3 min Intelligence Index: 49.7Claude Opus 5 (xhigh) · Anthropic Time per task: 12.2 min Intelligence Index: 49.7Claude Fable 5.1 (medium with fallback) · Anthropic Time per task: 5.6 min Intelligence Index: 49.1Claude Opus 5 (high) · Anthropic Time per task: 9.1 min Intelligence Index: 48.2Muse Spark 1.3 (max) · Meta Time per task: 5.4 min Intelligence Index: 48.2GPT-6.1 Sol (medium) · OpenAI Time per task: 2.1 min Intelligence Index: 47.8GPT-6 Sol (max) · OpenAI Time per task: 6.8 min Intelligence Index: 47.5GPT-5.6 Sol (max) · OpenAI Time per task: 8.0 min Intelligence Index: 47.1Claude Opus 5.5 …
25 of 25 models with both measures

02 / Evidence

Benchmark results

4 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.

Explore all models
Benchmark landscape
Humanity's Last Exam across models
Compare evaluation scores against operating cost, latency, or throughput.
Selected · Phi-4 Multimodal467 scored models5.0% · #371

Model positions

Humanity's Last Exam · highest score first · 467 models

Phi-4 Multimodal is #371 of 467 · 5.0%
Most attractive regionLeast attractive regionPareto frontierAnthropicOpenAIXiaomi
$0.00$2.36$4.72$7.08$9.450%17%33%50%66%Cost per task (USD)Humanity's Last ExamClaude Opus 5.5 (max with fallback) · Anthropic Cost per task: $5.98 Humanity's Last Exam: 61%Claude Fable 5.1 (max with fallback) · Anthropic Cost per task: $7.63 Humanity's Last Exam: 59%Claude Fable 5.1 (xhigh with fallback) · Anthropic Cost per task: $5.98 Humanity's Last Exam: 59%Claude Opus 5.5 (xhigh with fallback) · Anthropic Cost per task: $3.46 Humanity's Last Exam: 58%Claude Fable 5.1 (high with fallback) · Anthropic Cost per task: $3.91 Humanity's Last Exam: 56%Claude Opus 5.5 (high with fallback) · Anthropic Cost per task: $1.82 Humanity's Last Exam: 56%Claude Fable 5 (with fallback) · Anthropic Cost per task: $8.75 Humanity's Last Exam: 55%Claude Sonnet 5.5 (max with fallback) · Anthropic Cost per task: $7.60 Humanity's Last Exam: 55%Claude Opus 5 (max) · Anthropic Cost per task: $5.86 Humanity's Last Exam: 55%Claude Opus 5.5 (medium with fallback) · Anthropic Cost per task: $1.34 Humanity's Last Exam: 55%GPT-6 Astra (max) · OpenAI Cost per task: $3.26 Humanity's Last Exam: 55%GPT-6 Astra (xhigh) · OpenAI Cost per task: $2.31 Humanity's Last Exam: 55%Claude Opus 5 (xhigh) · Anthropic Cost per task: $4.88 Humanity's Last Exam: 54%Claude Fable 5.1 (medium with fallback) · Anthropic Cost per task: $2.98 Humanity's Last Exam: 54%GPT-6 Astra (high) · OpenAI Cost per task: $1.72 Humanity's Last Exam: 53%GPT-6.1 Sol (max) · OpenAI Cost per task: $0.72 Humanity's Last Exam: 53%Claude Opus 5 (high) · Anthropic Cost per task: $3.61 Humanity's Last Exam: 53%GPT-6 Astra (medium) · OpenAI Cost per task: $1.54 Humanity's Last Exam: 53%GPT-6.1 Sol (xhigh) · OpenAI Cost per task: $0.39 Humanity's Last Exam: 53%GPT-6.1 Sol (high) · OpenAI Cost per task: $0.32 Humanity's Last Exam: 51%Claude Opus 5 (medium) · Anthropic Cost per task: $2.19 Humanity's Last Exam: 51%Claude Sonnet 5.5 (xhigh with fallback) · Anthropic Cost per task: $2.74 Humanity's Last Exam: 50%GPT-6.1 Sol (medium) · OpenAI Cost per task: $0.21 Humanity's Last Exam: 50%GPT-5.6 Sol (max) · OpenAI Cost per task: $1.99 Humanity's Last Exam: 49%MiMo-V2.6-Pro · Xiaomi Cost per task: $0.13 Humanity's Last Exam: 49%Claude Opus 5.5 …
25 of 180 models with both measures

03 / Operation

Speed, tokens & price

Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.

Token pricing

Input / 1M
$0.00
Output / 1M
$0.00
Cache read / 1M
—
Cache write / 1M
—
Cache-hit discount
—

Response & usage

Output speed
17.2 tok/s
First chunk
1ms
First answer
1ms
Output / task
—
Reasoning / task
—

Evaluation workload

Canonical input
—
Canonical output
—
Answer / task
—
Index time / task
—
Run cost
—

By prompt type

PromptOutput speedFirst chunkFirst answerEnd to end
Medium17.3 tok/s0ms0ms29ms
Long17.2 tok/s1ms1ms30ms
Hundred K16.7 tok/s15ms15ms45ms
Medium Parallel17 tok/s1ms1ms30ms

04 / Access

License & availability

Recorded license

MIT

The publisher-linked license text defines permitted use and redistribution. Review it before using the model.

Weight access
Open weights
Classification
Permissive
Reasoning
No

Routing and providers

No reliable OpenRouter catalog match was captured for this model.

05 / Audit

Underlying fields

Inspect the captured model and routing records. Artificial Analysis destination links are omitted.