Gemma 3 12B Instruct
Context 128K tokens
Top 2 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 | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | DeepInfravia OpenRouter — Price via OpenRouter: OpenRouter's price for DeepInfra's endpoint (https://openrouter.ai/google/gemma-3-12b-it/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for DeepInfra's endpoint (https://openrouter.ai/google/gemma-3-12b-it/providers), collected 2026-11-03. | $0.050 | $0.150 | |
| 2 | NextBitvia OpenRouter — Price via OpenRouter: OpenRouter's price for NextBit's endpoint (https://openrouter.ai/google/gemma-3-12b-it/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for NextBit's endpoint (https://openrouter.ai/google/gemma-3-12b-it/providers), collected 2026-11-03. | $0.075 | $0.150 |
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one1.0
Thin data · 2/7Based on only 2 of 7 Composite inputs — treat this rank as uncertainAA Coding v4.x 5.8Coding Agent v1.4 —AA Intelligence (est.) 1.8AA Agentic 0.1Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
24 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Agentic
GDPval-AA v21-170 Elo
GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench Hard (AA)130.8%
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)10.0%
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 Index10.10
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) v1.0.1116.4%
SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index v4.x · frozen 2026-10-2755.80
AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).
Instruction-following
IFBench (AA single-turn)3036.7%
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)174.2%
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 Index4-77.1
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt2018.7
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)91.0%
GDP.pdf (AA) published 2026-09-10 → · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.1158.3%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA)2118.3%
AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.
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)1134.9%
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 v1.0.610.2%
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)810.8%
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) v1.0.110.8%
τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Uncensored
UGI Willingness513.00
UGI Willingness published 2026-09-10 → · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI1820.9
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)437.5%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
Writing
EQ-Bench Creative Writing v3331,131 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 v1.113241.8
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 Score3370.6
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 Writing3229.9
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 · 24 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 SciCode (AA subproblems) v1.0.1
Why
Observed: 0.16435 fractionPeer mean 0.46304 · peer sd 0.10542 · n 183 · families 125Directed z -2.833 · baseline z -1.087 · gap -1.746 · profile n 230.16435 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: SciCode (AA subproblems) · v1.0.1 · Published boardExact value:0.164351851851852fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:2e6400f5-85ca-4ebc-ba8f-c2811a631138:scicode
Missing coverage · 295 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 · 2 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
2 offers within the active global filters; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (2)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/google/gemma-3-12b-it/providers, collected 2026-11-03.
| DeepInfra | globaldeepinfra/bf16 | $0.050 raw in $/1M | $0.150 raw out $/1M | |
| NextBit | globalnextbit/int4EU | $0.075 raw in $/1M | $0.150 raw out $/1M |