Llama 3.3 Instruct 70B
Output 90 tokens/sFirst token 0.6 sContext 128K tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | DeepInfra | OpenRouter | $0.100 | $0.320 | |
| 2 | Novita | OpenRouter | $0.135 | $0.400 | |
| 3 | AkashML | OpenRouter | $0.200 | $0.520 | |
| 4 | Parasail | OpenRouter | $0.220 | $0.500 | |
| 5 | Groq | OpenRouter | $0.590 | $0.790 |
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one10.2
AA Coding 11.9Coding Agent v1.4 —AA Intelligence 7.7AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
20 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
GDPval-AA v2650 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
ITBench-AA00.6%
ITBench-AA published 2026-09-10 ↗ · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.
Terminal-Bench Hard (AA)233.0%
Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
Terminal-Bench v2.1 (AA)124.9%
Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
τ²-Bench Airline (OpenRouter run)938.7%
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.)
Coding
AA Coding Index1211.9
AA Coding Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task96$0.00079
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 task92$0.012
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)5547.1%
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 Index26-54.2
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt6831.4
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.
Long-context
AA-LCR v1.12015.7%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA) v2025127.7%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
AA Intelligence Index327.70
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
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)2449.8%
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)749.2%
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)3226.6%
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 Willingness694.00
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI7337.9
UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Writing
UGI Writing3126.2
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 · 22 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 ITBench-AA published 2026-09-10
Why
Observed: 0.00565 fractionPeer mean 0.31758 · peer sd 0.13369 · n 33 · families 31Directed z -2.333 · baseline z -0.649 · gap -1.684 · profile n 210.00565 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: ITBench-AA · published 2026-09-10 · Published boardExact value:0.00564971751412429fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:976cc8ad-7904-4056-83c5-960181f47d5f:itBenchSre
Missing coverage · 123 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 · 13 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
13 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (10)
| DeepInfra | globaldeepinfra/turbo | $0.100 raw in $/1M | $0.320 raw out $/1M | |
| Novita | globalnovita/bf16 | $0.135 raw in $/1M | $0.400 raw out $/1M | |
| AkashML | globalakashml/fp8 | $0.200 raw in $/1M | $0.520 raw out $/1M | |
| Parasail | globalparasail/fp8 | $0.220 raw in $/1M | $0.500 raw out $/1M | |
| Groq | globalgroq | $0.590 raw in $/1M | $0.790 raw out $/1M | |
| SambaNova | globalsambanova-turbo | $0.450 raw in $/1M | $0.900 raw out $/1M | |
| CoreWeave | globalcoreweave/fp16 | $0.710 raw in $/1M | $0.710 raw out $/1M | |
| globalgoogle-vertex/us-central1 | $0.720 raw in $/1M | $0.720 raw out $/1M | ||
| globalgoogle-vertex | $0.720 raw in $/1M | $0.720 raw out $/1M | ||
| Together | globaltogether | $1.04 raw in $/1M | $1.04 raw out $/1M |
STACKIT (1)
| STACKIT | eu01EU | $0.516 raw in $/1M | $0.745 raw out $/1M |
OVHcloud (1)
| OVHcloud | euEU | $0.770 raw in $/1M | $0.770 raw out $/1M |
Scaleway (1)
| Scaleway | euEU | $1.03 raw in $/1M | $1.03 raw out $/1M |