Qwen3.8 27B (Non-reasoning)
Output 49 tokens/sFirst token 1.2 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 one49.4
includes −1.6 for its Benchmaxxing signal (from 51.0; why, switch off in Options)
AA Coding 44.6Coding Agent v1.4 —AA Intelligence 22.4AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
12 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
GDPval-AA v2591,137 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v2.1 (AA)4849.1%
Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
Coding
SciCode (AA subproblems) v1.0.11736.2%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index5044.6
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.
Knowledge
Humanity's Last Exam (AA text-only)6112.1%
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 Index75-7.95
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
AA-LCR v1.16569.3%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Reasoning
AA Intelligence Index7522.4
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.
Safety/Alignment
BullshitBench V1 (clear pushback)9676.4%
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)9779.0%
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)530.3%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)7081.8%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
Tool-use
τ³-Banking (AA) v1.0.15220.0%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Vision
MMMU Pro (AA)5269.9%
MMMU Pro (AA) published 2026-09-10 ↗ · Published board — Tests multimodal understanding using challenging ten-option questions.
Unusual results
1 threshold-crossing signal flagged · 14 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 strong BullshitBench V1 (clear pushback) published 2026-09-10
Why
Observed: 0.7636 fractionPeer mean 0.3191 · peer sd 0.21942 · n 69 · families 57Directed z 2.026 · baseline z 0.278 · gap 1.748 · profile n 130.7636 fractionmeasuredobserved 2026-09-15raw.githubusercontent.com ↗Evidence
Axis: BullshitBench V1 (clear pushback) · published 2026-09-10 · Published boardExact value:0.7636fractionObserved: 2026-09-15T01:07:18.318850+00:00 · publication date: not recordedObservation id:public:37e290b5930a94abaf7d9776
Missing coverage · 131 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 |