ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

OpenAIOpen weightsReleased 5 Aug 2025

gpt-oss-20b benchmarks, speed and API pricing

Reviewed by Suhas Bhairav · Tested

Compare

Available through OpenRouter on

  • Darkbloom$0.018 in · $0.09 out
  • AkashML$0.02 in · $0.1 out
  • CoreWeave$0.03 in · $0.13 out
  • DekaLLM$0.029 in · $0.14 out
  • DeepInfra$0.03 in · $0.14 out
  • Parasail$0.03 in · $0.15 out
  • Amazon Bedrock$0.07 in · $0.15 out
  • SiliconFlow$0.04 in · $0.18 out
  • Google$0.07 in · $0.25 out
  • Groq$0.075 in · $0.3 out
Intelligence51.2% correct#46 of 72
Speed103tok/s#36 of 72
Cost$0.000066per question#2 of 72List $0.018 in · $0.09 out per 1M
Verbosity472tokens per question#13 of 72

Summary

  • Answers 41 of 80 verification questions correctly (51.2%), placing #46 of 72 models tested on the current suite.
  • Generates 103 output tokens per second, faster than 51% of the models the leaderboard measures.
  • Starts responding after 0.7 s (median time to first token), including thinking time.
  • Costs $0.000066 per question as billed, #2 cheapest of 12 models priced under $0.15 per 1M tokens.

Specifications

Reasoning
Yes
Input
text
Output
text
Context window
131k tokens
Knowledge cutoff
30 Jun 2024
OpenRouter ID
openai/gpt-oss-20b
Last tested
26 Oct 2026

Peer group: 13 models with a blended list price under $0.15 per 1M tokens (3 input : 1 output). Charts below compare gpt-oss-20b with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

gpt-oss-20b circled; dashed line joins models no cheaper model beats

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BMuse WonderGrok 4.7o3gpt-oss-20bGranite 4.0 MicroNova Micro 1.0Mercury 2.5Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-5.4GPT-6 Lunagpt-oss-120b

Score vs. end-to-end response time

gpt-oss-20b circled · accurate and quick sits top left

Most attractive quadrant02550751000 s25 s50 s75 s100 sEnd-to-end response time (s) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Llama 4 ScoutGemma 4 26B A4BLing 3.1 FlashHermes 4 405BMuse WonderGranite 4.0 MicroSolar Pro 4DeepSeek V4 Pro 0813Mistral Large 4Claude Opus 5.5Llama 4 MaverickKimi K3.1 Pro

Score vs. tokens per question

gpt-oss-20b circled · output tokens, reasoning included

Most attractive quadrant02550751001001,00010,000Output tokens per question (log) →Verification score (%) →Command AReka Flash 3Llama 4 ScoutQwen3.7 PlusGemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BClaude Fable 5.1GPT-6 AstraMuse WonderGrok 4.7o3gpt-oss-20bGranite 4.0 MicroNova Micro 1.0Mercury 2.5Granite 4.2 8BMinistral 3 14B 2512Hy3GLM 5.3 FlashSolar Pro 4Qwen3.6 35B A3BInkling SmallNemotron 3 UltraClaude Opus 5.5Gemini 4 ArgonGPT-5.4GPT-6 SolMiMo-V2.6-Pro

Verification score

All models tested on the current suite

  1. 1Claude Opus 5.585.0
  2. 2Gemini 4 Argon83.8
  3. 3GPT-5.3-Codex82.5
  4. 3Gemini 3.8 Flash82.5
  5. 5Claude Fable 5.181.2
  6. 6Grok 4.780.0
  7. 7Muse Wonder78.8
  8. 7Claude Sonnet 5.578.8
  9. 9Gemini 3.1 Pro Preview77.5
  10. 9Muse Spark Open77.5
  11. 46gpt-oss-20b51.2

61 more models · see the full leaderboard

6 of 78 tested models have no verification score

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, as billed

All models · lower is better

  1. 1Granite 4.0 Micro$0.000051
  2. 2gpt-oss-20b$0.000066
  3. 3Granite 4.2 8B$0.000077
  4. 4Nova Micro 1.0$0.000087
  5. 5Mercury 2.5$0.00011
  6. 6Phi 4$0.00012
  7. 7gpt-oss-120b$0.00013
  8. 8GLM 5.3 Flash$0.00015
  9. 9Ministral 3 3B 2512$0.00019
  10. 10GPT-6 Luna$0.00025

62 more models · see the full leaderboard

6 of 78 tested models have no cost per question
  • LFM2.5-2.6B: no verification score (80 of 80 questions failed on the host's side)
  • Ling 3.0 Flash VL: no verification score (not yet run on the current question suite)
  • Qwen3.5-122B-A10B: no verification score (not yet run on the current question suite)
  • Qwen3 Next 80B A3B Thinking: no verification score (not yet run on the current question suite)
  • Nova Premier 1.0: no verification score (not yet run on the current question suite)
  • GPT-5.5 Pro: no verification score (not yet run on the current question suite)

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Latency vs. output speed

gpt-oss-20b circled · quick to start and fast sits top left

Most attractive quadrant02004006008000.0 s5.0 s10.0 s15.0 s20.0 sTime to first token (s) →Output speed (tok/s) →Nemotron 3.5 Super VLQwen3.5 397B A17BMuse WonderMinistral 3 3B 2512Trinity Large ThinkingGemini 3.5 Flash LiteGemini 3.1 Pro PreviewGemini 3.8 FlashGemini 4 Argon

Results by category

Questions answered correctly in each category

Science18/30
Engineering4/15
Medicine4/11
Economics6/9
Law2/6
Humanities & social science7/9

More from OpenAI

OpenAI#3GPT-5.3-Codex82.5% verification score95 tok/s1.4 s first token$0.01 / questionOpenAI#12GPT-6 Astra76.2% verification score49 tok/s1.3 s first token$0.013 / questionOpenAI#12GPT-6.1 Terra Pro76.2% verification score— tok/s8.5 s first token$0.005 / question

All OpenAI models →

Compare gpt-oss-20b

Head to head with its closest rivals, other OpenAI models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

HostInput / 1MOutput / 1MContextMax outputQuantization
Darkbloom$0.018$0.09131k33kfp8
AkashML$0.02$0.1131k118kfp4
CoreWeave$0.03$0.13131k118kfp4
DekaLLM$0.029$0.14131k118kbf16
DeepInfra$0.03$0.14131k118kbf16
Parasail$0.03$0.15131k118kfp4
Amazon Bedrock$0.07$0.15131k118k—
SiliconFlow$0.04$0.18131k8kfp8
Google$0.07$0.25131k33k—
Groq$0.075$0.3131k66k—

gpt-oss-20b: frequently asked questions

How accurate is gpt-oss-20b?
gpt-oss-20b answered 41 of 80 questions correctly (51.2%) in the 2026-10-27 run, ranking #46 of 78 models.
How fast is gpt-oss-20b?
gpt-oss-20b generated a median of 103 output tokens per second in the 2026-10-27 run, ranking #36 of 78. Median time to first token was 0.7 s.
What is the latency of gpt-oss-20b?
gpt-oss-20b had a median time to first token of 0.7 s in the 2026-10-27 run, ranking #35 of 78 models.
How much does gpt-oss-20b cost?
gpt-oss-20b cost $0.000066 per question on average as billed in the 2026-10-27 run, reasoning tokens included.
What is gpt-oss-20b API pricing?
gpt-oss-20b is listed at $0.018 per million input tokens and $0.09 per million output tokens on OpenRouter.
What is the context window of gpt-oss-20b?
gpt-oss-20b accepts up to 131,072 tokens of context, according to OpenRouter's model catalogue.
Is gpt-oss-20b open source?
Yes. gpt-oss-20b is an open-weights model: OpenAI publishes the weights, so you can run it yourself as well as through an API.
Who makes gpt-oss-20b?
gpt-oss-20b is made by OpenAI. The LLM Verifications Leaderboard tested it through OpenRouter using the model ID openai/gpt-oss-20b.
Where can I use gpt-oss-20b via API?
Through OpenRouter, gpt-oss-20b is served by 8 hosts: AkashML, Amazon Bedrock, CoreWeave, Darkbloom, DekaLLM, Groq, Parasail, SiliconFlow.