o4-mini (High)
Context 200K tokens
Top 1 cheapest providers (Adjusted $/task)
Within the active global provider, residency and confidentiality filters.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Azure AI Foundrydirect — Direct price: Azure AI Foundry's own price list (https://prices.azure.com/api/retail/prices), collected 2026-11-03. | direct — Direct price: Azure AI Foundry's own price list (https://prices.azure.com/api/retail/prices), collected 2026-11-03. | $1.10 | $4.40 |
Composite
3 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one20.4
AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 6.3AA Agentic —Epoch ECI 145.6Software ECI 145.0DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
15 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
Agentic
Terminal-Bench Hard (AA)5215.2%
Terminal-Bench Hard (AA) pinned revision 74221fb → · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
Coding
GSO software optimization, Opt@1 (UC Berkeley) opt1-102223.6%
GSO software optimization, Opt@1 (UC Berkeley) opt1-102 → · OpenHands — An agent gets a real codebase and a performance test and must make the code as fast as an expert developer's optimization; 102 tasks across 10 codebases and 5 languages.
Instruction-following
IFBench (AA single-turn)8268.7%
IFBench (AA single-turn) published 2026-09-10 → · Published board — Tests precise single-turn instructions with deterministic rule checks.
Knowledge
Humanity's Last Exam (AA text-only)6616.5%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index50-35.7
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
AA-LCR v1.15461.0%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA)9290.7%
AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Safety/Alignment
BullshitBench V1 (clear pushback)1510.9%
BullshitBench V1 (clear pushback) published 2026-09-10 → · Published board — Whether a model rejects the broken premise of 55 deliberately nonsensical prompts (V1 question set) instead of answering them confidently.
BullshitBench V2 (clear pushback)24.0%
BullshitBench V2 (clear pushback) published 2026-09-10 → · Published board — Whether a model rejects the broken premise of 100 deliberately nonsensical prompts (V2 question set) instead of answering them confidently.
Science
CritPt (AA)570.6%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)6478.4%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
Tool-use
τ²-Bench Telecom (AA)5655.6%
τ²-Bench Telecom (AA) published 2026-09-10 → · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
VitaBench 2026-01-227119.5%
VitaBench 2026-01-22 → · Published board — Can an agent finish a real-life errand that spans food delivery, restaurant bookings and travel — 66 tools, a customer whose wishes shift mid-conversation, and no domain policy to lean on?
Vision
MMMU Pro (AA)4869.2%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
CharXiv Reasoning val-v1.010072.0%
CharXiv Reasoning val-v1.0 → · validation — Can a multimodal model reason over the real, messy charts in scientific papers — combining values, trends and labels across a figure — rather than read off templated plots?
Missing coverage · 304 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Token offers by platform · 2 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
2 offers within the active global filters; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
Azure AI Foundry (2)
Direct prices from Azure AI Foundry's own price list. Source: prices.azure.com/api/retail/prices, collected 2026-11-03.
| Azure AI Foundry | global | $1.10 raw in $/1M | $4.40 raw out $/1M | |
| Azure AI Foundry | euEU | $1.21 raw in $/1M | $4.84 raw out $/1M |