Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is gpt-oss-20b?

95 SI-IQ · 90% interval 89–101
Not ranked: too little data

gpt-oss-20b is a model from OpenAI, released on Aug 5, 2025. Its SI-IQ is 95 (90% interval 89–101), estimated from 3 benchmark results by 2 independent evaluators.

This model has fewer than 5 independent benchmark results or fewer than 2 different evaluators, so it is shown but not ranked.

Facts

Developer: OpenAI
Released: Aug 5, 2025
Access: Open weights (restricted licence)
Benchmarks used: 3 results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
OTIS Mock AIME 2024–2025	Math	65.3%	100	Epoch AI	`gpt-oss-20b_medium`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	60.8%	85	Epoch AI	`gpt-oss-20b_medium`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	63.1%	89	OpenRouter	`openai/gpt-oss-20b` Darkbloom · median over providers (10 of 10 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file
τ²-bench Airline (OpenRouter run)	Agents	46.7%	84	OpenRouter	`openai/gpt-oss-20b` Amazon Bedrock, CoreWeave, Darkbloom, DeepInfra, Groq, Parasail, PrimeIntellect · median over providers (7 of 7 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, gpt-oss-20b has a rating of 1,317 (1,311–1,324) from 10,419 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..