Models / gpt-oss-120b

OpenAI

gpt-oss-120b

gpt-oss-120b trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.20.

Results 16 Nov 2026 · 40 results · 6 sources

Test gpt-oss-120b on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.10 in · $0.50 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
259 tokens a second; on its test prompt the answer starts after 8.2 s, thinking time included
Artificial Analysis, on its usual API, at high reasoning; 258–259 across 2 settings
Intelligence Index
11.6
Artificial Analysis, at high reasoning; 10.2–11.6 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights published
Released
5 Aug 2025
131,072 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 129th of 185Claude Opus 5.5 – $0.20 blended, 18th percentilecheapest: Mistral Nemo 7th of 65Nemotron 3.5 Super VL
Models priced under $0.25 per million tokens 15th of 41Claude Haiku 5.5 – sets this group 4th of 19Nemotron 3.5 Super VL
Models with similar intelligence sets this group – $0.20 blended, 22nd percentilecheapest: gpt-oss-20b 2nd of 13gpt-oss-20b
Models writing 200 or more tokens a second 10th of 14Muse Spark 1.3 – $0.20 blended, 31st percentilecheapest: gpt-oss-20b sets this group
Models from developers based in the US 68th of 92Claude Opus 5.5 – $0.20 blended, 18th percentilecheapest: Gemma 3 4B 5th of 33Nemotron 3.5 Super VL
Open-weights models 61st of 104MiMo-V2.6-Pro – $0.20 blended, 26th percentilecheapest: Mistral Nemo 5th of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 125th of 159 available · 19th of 37 at its price
Benchmarkgpt-oss-120bRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 26.2% 79th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 12.8% 63rd of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $-21.53 51st of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 49th of 51 available · 4th of 4 at its price
Benchmarkgpt-oss-120bRank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 4.4% 37th of 37 Claude Sonnet 5.5 75.5%
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 118th of 187 available · 13th of 41 at its price
Benchmarkgpt-oss-120bRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 11.6 129th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 19.6% 104th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 78.2% 100th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 124th of 169 available · 13th of 39 at its price
Benchmarkgpt-oss-120bRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,352 119th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 38.5 86th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 129th of 139 available · 24th of 30 at its price
Benchmarkgpt-oss-120bRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 14.2% 62nd of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,385 103rd of 109 Gemini 4 Argon 1,511
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against gpt-oss-120b at $0.20 blended, Intelligence Index 11.6. "Similar intelligence" means within 4 points or better.

Where to run it

25 hosts on OpenRouter at the standard service tier, with a median of $0.20 blended per million tokens; quantisation where the host states it: FP4, INT4, BF16, FP8, FP16. Cheapest first.

HostQuantisationInputOutputBlended
Near AIFP4$0.03$0.15$0.06
VeniceINT4$0.03$0.15$0.06
CoreWeaveFP4$0.03$0.17$0.07
DekaLLMBF16$0.03$0.18$0.07
AkashMLFP4$0.03$0.19$0.07
DeepInfraBF16$0.04$0.17$0.07
PrimeIntellectFP4$0.06$0.12$0.07
CrusoeBF16$0.05$0.25$0.10

Other service tiers, not counted above: Parasail fast $0.15 in, $0.75 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 17 dearer hosts are left out.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

gpt-oss-120bClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent with open weights
Price per million tokens $0.20 $0.20$0.06$8.00$0.54
Tokens a second 259 2402779643
Intelligence Index 11.6 43.410.057.646.3
Spring Prompt overall – 40–82–
Rank among available models, by use case
Product listings – 20th–13th–
Decks from an analysis – 18th–7th–
User surveys – 7th–4th–
Marketing planning – 30th–9th–
Agents and tool use 125th of 159 28th130th3rd23rd
Professional work 49th of 51 ––3rd–
Reasoning and knowledge 118th of 187 25th132nd1st13th
Writing 124th of 169 –155th5th23rd
Sticking to the facts 129th of 139 ––3rd10th
Speed under pressure – 21st–––

Shaded figures are better than gpt-oss-120b's. A dash means no result.

Where it has been measured

2nd fastest of the 13 models with similar intelligence. 15th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, professional work, and sticking to the facts.

Every result

40 published results from 6 sources, each in the source's own units, with the configuration that produced it.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 4.4% 39 of 39 gpt-oss-120b 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,385
1,378–1,391
161 of 182 gpt-oss-120b 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,352
1,343–1,360
208 of 406 gpt-oss-120b 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,278
1,268–1,288
264 of 411 gpt-oss-120b 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,357
1,341–1,373
213 of 363 gpt-oss-120b 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,323
1,316–1,330
230 of 413 gpt-oss-120b 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,352
1,347–1,356
212 of 413 gpt-oss-120b 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,309
1,302–1,317
241 of 412 gpt-oss-120b 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 26 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 30.4 136 of 187 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 21.2 152 of 187 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 11.6 298 of 413 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 10.2 317 of 413 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 78.2% 189 of 360 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 67.2% 261 of 360 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 19.6% 204 of 419 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 5.9% 332 of 419 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 69.0% 70 of 288 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 58.3% 110 of 288 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 52.0% 276 of 407 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 46.0% 291 of 407 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 259 9 of 137 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 258 10 of 137 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 34.0% 185 of 205 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 26.2% 140 of 188 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 13.9% 151 of 188 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 23.5% 138 of 282 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 5.3% 232 of 282 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 8.22 54 of 137 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 8.27 55 of 137 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 12.8% 112 of 175 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 2.9% 171 of 175 gpt-oss-120b (low reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 65.8% 137 of 286 gpt-oss-120b (high reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 45.0% 173 of 286 gpt-oss-120b (low reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 107.0% 362 of 379 gpt-oss-120b (medium reasoning) 1 Oct 2025
UGI: style adherencescore from 0 to 1, higher is better 0.29 360 of 379 gpt-oss-120b (medium reasoning) 1 Oct 2025
UGI: writing scorescore out of 100, higher is better 38.5 235 of 379 gpt-oss-120b (medium reasoning) 1 Oct 2025

Not shown: Not other format limits such as character counts or bullet counts.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.9% 19 of 108 gpt-oss-120b 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 14.2% 90 of 108 gpt-oss-120b 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $-21.53 61 of 63 gpt-oss-120b 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will gpt-oss-120b work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.