gpt-oss-120b (high)
Output 182 tokens/sFirst token 0.5 sContext 131K 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 | AkashML | OpenRouter | $0.030 | $0.170 | |
| 2 | CoreWeave | OpenRouter | $0.030 | $0.170 | |
| 3 | DekaLLM | OpenRouter | $0.030 | $0.180 | |
| 4 | DeepInfra | OpenRouter | $0.037 | $0.170 | |
| 5 | DigitalOcean | OpenRouter | $0.060 | $0.420 |
Composite
4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one25.6
includes −1.3 for its Benchmaxxing signal (from 26.9; why, switch off in Options)
AA Coding 30.4Coding Agent v1.4 —AA Intelligence 12.3AA Agentic 6.2Epoch ECI 140.1Software ECI 138.9DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
29 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
Agentic
APEX-Agents-AA103.1%
APEX-Agents-AA published 2026-09-10 ↗ · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.
GDPval-AA v235745 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Harvey LAB-AA013.9%
Harvey LAB-AA published 2026-09-10 ↗ · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.
ITBench-AA65.6%
ITBench-AA published 2026-09-10 ↗ · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.
Terminal-Bench Hard (AA)6323.5%
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)3026.2%
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)180.0%
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.
τ²-Bench Airline (OpenRouter run)3764.1%
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 Index356.20
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) v1.0.11434.0%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index3730.4
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 task73$0.0071
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 task91$0.013
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)8369.0%
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)7119.6%
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 Index34-49.3
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
GDP.pdf (AA)284.0%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.14852.0%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
MLCR-AA81.1%
MLCR-AA published 2026-09-10 ↗ · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.
Math
AIME 2025 (AA) v20259593.4%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
Mystery Game Puzzles (Epoch AI)00.0%
Mystery Game Puzzles (Epoch AI) published 2026-09-18 ↗ · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.
AA Intelligence Index5312.3
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)13.6%
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)45.0%
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)651.1%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)6478.2%
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)3474.9%
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 v1.0.640.2%
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
EnterpriseOps-Gym-AA425.5%
EnterpriseOps-Gym-AA published 2026-09-10 ↗ · Published board — Tests enterprise workflows through MCP tools against resettable application environments.
τ²-Bench Telecom (AA)6065.8%
τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
τ³-Banking (AA) v1.0.13712.8%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Unusual results
1 threshold-crossing signal flagged · 30 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 Harvey LAB-AA published 2026-09-10
Why
Observed: 0.13895 fractionPeer mean 0.79402 · peer sd 0.17289 · n 43 · families 38Directed z -3.789 · baseline z -0.432 · gap -3.357 · profile n 290.13895 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: Harvey LAB-AA · published 2026-09-10 · Published boardExact value:0.138949196699957fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:f0083258-8646-45b8-8082-7aaf6c2ea82a:harveyLab
Missing coverage · 114 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 |
|---|---|---|
| gpt-oss-120b (high) | 30.4 | 12.3 |
| gpt-oss-120b (low) | 21.2 | 10.2 |
Token offers by platform · 33 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
33 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (23)
| AkashML | globalakashml/bf16 | $0.030 raw in $/1M | $0.170 raw out $/1M | |
| CoreWeave | globalcoreweave/fp4 | $0.030 raw in $/1M | $0.170 raw out $/1M | |
| DekaLLM | globaldekallm/bf16 | $0.030 raw in $/1M | $0.180 raw out $/1M | |
| DeepInfra | globaldeepinfra/bf16 | $0.037 raw in $/1M | $0.170 raw out $/1M | |
| DigitalOcean | globaldigitalocean | $0.060 raw in $/1M | $0.420 raw out $/1M | |
| Crusoe | globalcrusoe/bf16 | $0.050 raw in $/1M | $0.250 raw out $/1M | |
| Novita | globalnovita/fp4 | $0.050 raw in $/1M | $0.250 raw out $/1M | |
| Mancer 2 | globalmancer/fp8 | $0.050 raw in $/1M | $0.300 raw out $/1M | |
| Parasail | globalparasail/fp4 | $0.100 raw in $/1M | $0.750 raw out $/1M | |
| BaseTen | globalbaseten/fp4 | $0.100 raw in $/1M | $0.500 raw out $/1M | |
| SiliconFlow | globalsiliconflow/fp8 | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Groq | globalgroq | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Amazon Bedrock | euamazon-bedrock/eu-west-1EU | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Nebius | globalnebius/fp4 | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Amazon Bedrock | globalamazon-bedrock | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| DeepInfra | globaldeepinfra/turbo | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Phala | globalphalaTEE | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| SambaNova | globalsambanova | $0.140 raw in $/1M | $0.950 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp8 | $0.200 raw in $/1M | $0.950 raw out $/1M | |
| Cerebras | globalcerebras/fp16 | $0.350 raw in $/1M | $0.750 raw out $/1M | |
| globalgoogle-vertex/global | $0.090 raw in $/1M | $0.360 raw out $/1M | ||
| Together | globaltogether | $0.150 raw in $/1M | $0.600 raw out $/1M | |
| Mara | globalmara | $0.150 raw in $/1M | $0.750 raw out $/1M |
Google Vertex AI (1)
| Google Vertex AI | global | $0.090 raw in $/1M | $0.360 raw out $/1M |
OVHcloud (1)
| OVHcloud | euEU | $0.090 raw in $/1M | $0.460 raw out $/1M |
T-Systems LLM Hub (1)
| T-Systems LLM Hub | euEU | $0.230 raw in $/1M | $0.740 raw out $/1M |
TrustedTokens (1)
| TrustedTokens | euEU | $0.170 raw in $/1M | $0.690 raw out $/1M |
Azure AI Foundry (1)
| Azure AI Foundry | global | $0.150 raw in $/1M | $0.600 raw out $/1M |
Nebius (1)
| Nebius | euEU | $0.150 raw in $/1M | $0.600 raw out $/1M |
Scaleway (1)
| Scaleway | euEU | $0.170 raw in $/1M | $0.690 raw out $/1M |
IONOS (1)
| IONOS | euEU | $0.170 raw in $/1M | $0.710 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1EU | $0.200 raw in $/1M | $0.790 raw out $/1M |
STACKIT (1)
| STACKIT | eu01EU | $0.516 raw in $/1M | $0.745 raw out $/1M |