Qwen2.5 Instruct 72B
Context 131K 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 | DeepInfravia OpenRouter — Price via OpenRouter: OpenRouter's price for DeepInfra's endpoint (https://openrouter.ai/qwen/qwen-2.5-72b-instruct/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for DeepInfra's endpoint (https://openrouter.ai/qwen/qwen-2.5-72b-instruct/providers), collected 2026-11-03. | $0.360 | $0.400 |
Composite
1 of 7 inputs6 radar axes: DesignArena's two boards share one5.9
Thin data · 1/7Based on only 1 of 7 Composite inputs — treat this rank as uncertaindominance-adjusted from 8.0: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 3.4AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
18 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
Terminal-Bench Hard (AA)294.5%
Terminal-Bench Hard (AA) pinned revision 74221fb → · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
τ²-Bench Airline (OpenRouter run)326.0%
τ²-Bench Airline (OpenRouter run) published 2026-09-15 → · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task94$0.00098
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 → · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task40$0.079
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 → · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.
Instruction-following
IFBench (AA single-turn)3136.9%
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)63.6%
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 Index27-53.1
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt2921.8
UGI NatInt published 2026-09-10 → · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.
Math
AIME 2025 (AA)1714.0%
AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Roleplay
Japanese-RP-Bench (Aratako)1004.21
Japanese-RP-Bench (Aratako) published 2026-09-10 → · Published board — Benchmark measuring LLM Japanese roleplay ability via 10-turn two-model dialogues scored by a four-judge ensemble across eight criteria.
Science
CritPt (AA)240.0%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)2349.1%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)644.6%
GPQA Diamond (OpenRouter run) published 2026-09-15 → · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
τ²-Bench Telecom (AA)4234.5%
τ²-Bench Telecom (AA) published 2026-09-10 → · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
Uncensored
UGI Willingness422.80
UGI Willingness published 2026-09-10 → · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI3527.4
UGI published 2026-09-10 → · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Writing
BuzzBench2045.9
BuzzBench published 2026-09-10 → · Published board — An LLM-judged evaluation of humour explanation and predicted audience response to Never Mind the Buzzcocks introductions.
UGI Writing3831.5
UGI Writing published 2026-09-10 → · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.
Unusual results
1 threshold-crossing signal flagged · 16 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually weak τ²-Bench Airline (OpenRouter run) published 2026-09-15
Why
Observed: 0.26042 fractionPeer mean 0.63068 · peer sd 0.16015 · n 117 · families 117Directed z -2.312 · baseline z -0.617 · gap -1.695 · profile n 150.26042 fractionmeasured± 0.013 sd· 96 tasks· 0.08 USD per task (measured by OpenRouter)observed 2026-09-15openrouter.ai ↗Evidence
Axis: τ²-Bench Airline (OpenRouter run) · published 2026-09-15 · Published boardExact value:0.26041658333333334fractionPublished standard deviation: 0.01347799999999999 fractionTasks evaluated: 96Published mean cost: 0.07850963541666667 USD per task (measured by OpenRouter) — measured by OpenRouter on τ²-Bench Airline (OpenRouter run)Observed: 2026-09-15T23:29:03.209Z · publication date: not recordedObservation id:openrouter:qwen/qwen-2.5-72b-instruct|tau_bench_verified_airlineSource: https://openrouter.ai/benchmarks
Missing coverage · 301 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 · 1 offer (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
1 offer 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.
OpenRouter (1)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/qwen/qwen-2.5-72b-instruct/providers, collected 2026-11-03.
| DeepInfra | globaldeepinfra/fp8 | $0.360 raw in $/1M | $0.400 raw out $/1M |