Qwen3.8 27B (xhigh)
Output 42 tokens/sFirst token 1.3 sContext 256K 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 | $0.150 | $1.88 | |
| 2 | Phala | OpenRouter | $0.199 | $2.08 | |
| 3 | Chutes | Chutes | $0.240 | $2.20 | |
| 4 | Chutes | OpenRouter | $0.240 | $2.20 | |
| 5 | Parasail | OpenRouter | $0.240 | $2.20 |
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one69.6
includes −1.6 for its Benchmaxxing signal (from 71.2; why, switch off in Options)
dominance-adjusted from 79.6: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding 68.1Coding Agent v1.4 —AA Intelligence 33.9AA Agentic 46.5Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
30 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
AA-Briefcase821,398 Elo
AA-Briefcase published 2026-09-10 ↗ · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
GDPval-AA v2841,463 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v2.1 (AA)8179.8%
Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
Terminal-Bench v4.0 (AA)645.6%
Terminal-Bench v4.0 (AA) v4.0 ↗ · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.
Vals Index v2 (Vals AI)2348.5%
Vals Index v2 (Vals AI) v2 ↗ · Published board — GDP-weighted average of agentic model performance across finance, coding and legal tasks.
Finance Agent v2 (Vals Index v2)2748.6%
Finance Agent v2 (Vals Index v2) v2 ↗ · Published board — Multi-step financial reasoning tasks.
Terminal-Bench 2.1 (Vals Index v2)2758.4%
Terminal-Bench 2.1 (Vals Index v2) v2 ↗ · Published board — Command-line interface problem solving, as run by Vals AI.
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)8011.3%
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 ↗ · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.
τ²-Bench Airline (OpenRouter run)9076.9%
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.)
AA Agentic Index8846.5
AA Agentic Index published 2026-09-18 ↗ · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Coding
SciCode (AA subproblems) v1.0.14846.6%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
Vibe Code Bench (Vals Index v2)3564.8%
Vibe Code Bench (Vals Index v2) v2 ↗ · Published board — End-to-end app-building tasks.
Code Migration (Vals Index v2 subset)1614.0%
Code Migration (Vals Index v2 subset) v2 ↗ · Published board — Porting projects to another language, including COBOL modernization.
AA Coding Index7768.1
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
Vals Index v2 cost per test (Vals AI)23$8.48
Vals Index v2 cost per test (Vals AI) v2 ↗ · Published board — Vals AI's published USD cost per test for each model on the Vals Index v2.
GPQA Diamond (OpenRouter run) — measured cost per task44$0.035
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 task39$0.08
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.
Knowledge
Humanity's Last Exam (AA text-only)8633.9%
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 Index72-9.98
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Legal Research Bench (Vals Index v2)3436.1%
Legal Research Bench (Vals Index v2) v2 ↗ · Published board — Case and statute research with citation-backed answers.
Long-context
GDP.pdf (AA)6616.4%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.19582.0%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
MLCR-AA7621.7%
MLCR-AA published 2026-09-10 ↗ · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.
Reasoning
AA Intelligence Index9033.9
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)805.4%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)9090.5%
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)5682.2%
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
AutomationBench-AA v1.0.67148.2%
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
EnterpriseOps-Gym-AA7244.2%
EnterpriseOps-Gym-AA published 2026-09-10 ↗ · Published board — Tests enterprise workflows through MCP tools against resettable application environments.
τ³-Banking (AA) v1.0.19848.0%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Excel Modeling Benchmark (Vals Index v2)3859.7%
Excel Modeling Benchmark (Vals Index v2) v2 ↗ · Published board — Building and editing financial models in spreadsheets.
Vision
MMMU Pro (AA)7576.3%
MMMU Pro (AA) published 2026-09-10 ↗ · Published board — Tests multimodal understanding using challenging ten-option questions.
Missing coverage · 113 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.
Variants / reasoning settings
Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| Qwen3.8 27B (xhigh) | 68.1 | 33.9 |
| Qwen3.8 27B (low) | 58.2 | 26.5 |
| Qwen3.8 27B (medium) | 56.1 | 27.8 |
| Qwen3.8 27B (Non-reasoning) | 44.6 | 22.4 |
Token offers by platform · 21 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
21 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (14)
| ModelRunfree — Free route: rate- and quota-limited, availability may change — not used as a paid price | globalmodelrun/fp4 | $0 raw in $/1M | $0 raw out $/1M | not a paid price |
| DeepInfra | globaldeepinfra/bf16 | $0.150 raw in $/1M | $1.88 raw out $/1M | |
| Phala | globalphalaTEE | $0.199 raw in $/1M | $2.08 raw out $/1M | |
| Chutes | globalchutes/fp8 | $0.240 raw in $/1M | $2.20 raw out $/1M | |
| Parasail | globalparasail/fp8 | $0.240 raw in $/1M | $2.20 raw out $/1M | |
| DekaLLM | globaldekallm | $0.200 raw in $/1M | $2.50 raw out $/1M | |
| AkashML | globalakashml/fp8 | $0.250 raw in $/1M | $2.20 raw out $/1M | |
| Ionstream | globalionstream/fp8 | $0.280 raw in $/1M | $2.55 raw out $/1M | |
| Reka | globalreka/fp8 | $0.214 raw in $/1M | $2.55 raw out $/1M | |
| Mancer 2 | globalmancer/fp8 | $0.200 raw in $/1M | $2.50 raw out $/1M | |
| Novita | globalnovita | $0.420 raw in $/1M | $3.00 raw out $/1M | |
| Io Net | globalio-net/fp8 | $0.300 raw in $/1M | $2.80 raw out $/1M | |
| CoreWeave | globalcoreweave/fp8 | $0.400 raw in $/1M | $3.00 raw out $/1M | |
| Venice | globalvenice/fp8 | $0.450 raw in $/1M | $3.20 raw out $/1M |
Chutes (1)
| Chutes | globalTEE | $0.240 raw in $/1M | $2.20 raw out $/1M |
TensorX (1)
| TensorX | euEU | $0.400 raw in $/1M | $2.40 raw out $/1M |
TrustedTokens (1)
| TrustedTokens | euEU | $0.460 raw in $/1M | $3.09 raw out $/1M |
Scaleway (1)
| Scaleway | euEU | $0.690 raw in $/1M | $3.78 raw out $/1M |
STACKIT (1)
| STACKIT | eu01EU | $0.516 raw in $/1M | $0.745 raw out $/1M |
IONOS (1)
| IONOS | euEU | $0.450 raw in $/1M | $2.70 raw out $/1M |
OVHcloud (1)
| OVHcloud | euEU | $0.460 raw in $/1M | $3.09 raw out $/1M |