Gemma 3 27B Instruct
Context 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 | Parasail | OpenRouter | $0.080 | $0.450 | |
| 2 | DeepInfra | OpenRouter | $0.080 | $0.160 | |
| 3 | Nebius | Nebius | $0.100 | $0.300 | |
| 4 | Nebius | OpenRouter | $0.100 | $0.300 | |
| 5 | Novita | OpenRouter | $0.119 | $0.200 |
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one4.3
AA Coding 10.1Coding Agent v1.4 —AA Intelligence 4.9AA Agentic 0.1Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
25 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
GDPval-AA v20-171 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench Hard (AA)263.8%
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)114.5%
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.
AA Agentic Index00.10
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) v1.0.1423.3%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index1010.1
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.
Instruction-following
IFBench (AA single-turn)1831.8%
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)214.4%
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 Index9-67.2
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt7934.5
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
GDP.pdf (AA)30.2%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.1157.3%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA) v20252220.7%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
AA Intelligence Index34.90
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)1842.8%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
Tool-use
AutomationBench-AA v1.0.620.2%
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
τ²-Bench Telecom (AA)710.5%
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) v1.0.110.8%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Uncensored
UGI Willingness142.00
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI2220.4
UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Vision
MMMU Pro (AA)1448.0%
MMMU Pro (AA) published 2026-09-10 ↗ · Published board — Tests multimodal understanding using challenging ten-option questions.
Writing
EQ-Bench Creative Writing v3391,263 Elo
EQ-Bench Creative Writing v3 v3 ↗ · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.
EQ-Bench Longform Creative Writing v1.113241.9
EQ-Bench Longform Creative Writing v1.11 ↗ · Published board — LLM-judged benchmark in which models plan and write a short story/novella over 8x 1000-word turns, scored 0-100 across 14 rubric dimensions.
Slop Score6769.5
Slop Score published 2026-09-10 ↗ · Published board — Leaderboard and analysis tool scoring how much model writing resembles AI slop via overused words, contrast patterns, and trigrams.
UGI Writing8945.0
UGI Writing published 2026-09-10 ↗ · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.
Missing coverage · 118 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 · 7 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
7 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (4)
| Parasail | globalparasail/fp8 | $0.080 raw in $/1M | $0.450 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp8 | $0.080 raw in $/1M | $0.160 raw out $/1M | |
| Novita | globalnovita/bf16 | $0.119 raw in $/1M | $0.200 raw out $/1M | |
| Nebius | globalnebius/fp8 | $0.100 raw in $/1M | $0.300 raw out $/1M |
Nebius (1)
| Nebius | euEU | $0.100 raw in $/1M | $0.300 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1EU | $0.276 raw in $/1M | $0.456 raw out $/1M |
STACKIT (1)
| STACKIT | eu01EU | $0.516 raw in $/1M | $0.745 raw out $/1M |