Compare · ModelsLive · 2 picked · head to head

GPT-5 vs gpt-oss-120b

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

GPT-5 wins 20 of 21 shared benchmarks. Leads in coding · agentic · knowledge.

Category leads
coding·GPT-5agentic·GPT-5knowledge·GPT-5general·GPT-5language·GPT-5math·gpt-oss-120breasoning·GPT-5

Head to head · from the data · data as of 2026-11-20

  • Benchmarks · GPT-5 leads on 20 of 21 shared benchmarks (Aider polyglot, APEX-Agents, Chess Puzzles, Dtbench, 16 more), gpt-oss-120b on 1 (HELM · Omni-MATH)
  • Price · GPT-5 input $1.25/M vs gpt-oss-120b $0.09/M, gpt-oss-120b is 93% cheaper (OpenRouter list price, as of 2026-11-20)
  • Cheapest provider · GPT-5 at Azure and 1 other provider $1.25/M input (of 2 offers) as of 2026-11-20 · gpt-oss-120b at AkashML and 4 other providers $0.03/M input (of 24 offers) as of 2026-11-20
  • Context · GPT-5 400K tokens vs gpt-oss-120b 131K tokens
  • Released · GPT-5 Aug 7, 2025 vs gpt-oss-120b Aug 5, 2025 · the same month
  • Open weights · gpt-oss-120b has open weights (on Hugging Face as openai/gpt-oss-120b)
  • Price history · GPT-5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-20

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
GPT-5
#117 by perf·#8 by attention
DESERVED
gpt-oss-120b
#142 by perf·no signal
QUIET
Best value
23.7x better value than GPT-5
GPT-5
9.3 pts/$
$5.63/M
gpt-oss-120b
219.1 pts/$
$0.22/M
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
GPT-5gpt-oss-120b
Aider polyglot
GPT-5 leads by +46.2
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
GPT-5
88.0
gpt-oss-120b
41.8
APEX-Agents
GPT-5 leads by +13.6
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5
18.3
gpt-oss-120b
4.7
Chess Puzzles
GPT-5 leads by +21.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5
37.0
gpt-oss-120b
15.8
Dtbench
GPT-5 leads by +24.0
GPT-5
84.5
gpt-oss-120b
60.5
Fiction.LiveBench
GPT-5 leads by +52.8
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
GPT-5
97.2
gpt-oss-120b
44.4
GPQA diamond
GPT-5 leads by +17.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5
85.0
gpt-oss-120b
67.7
HELM · GPQA
GPT-5 leads by +10.7
GPT-5
79.1
gpt-oss-120b
68.4
HELM · IFEval
GPT-5 leads by +3.9
GPT-5
87.5
gpt-oss-120b
83.6
HELM · MMLU-Pro
GPT-5 leads by +6.8
GPT-5
86.3
gpt-oss-120b
79.5
HELM · Omni-MATH
gpt-oss-120b leads by +4.1
GPT-5
64.7
gpt-oss-120b
68.8
HELM · WildBench
GPT-5 leads by +1.2
GPT-5
85.7
gpt-oss-120b
84.5
Lech Mazur Writing
GPT-5 leads by +8.7
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
GPT-5
86.0
gpt-oss-120b
77.3
Lmca
GPT-5 leads by +21.0
GPT-5
47.0
gpt-oss-120b
26.1
Metr Time Horizons
GPT-5 leads by +13.0
GPT-5
69.6
gpt-oss-120b
56.6
Mystery Game Puzzles
GPT-5 leads by +15.2
GPT-5
15.2
gpt-oss-120b
0.0
OTIS Mock AIME 2024-2025
GPT-5 leads by +2.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5
91.4
gpt-oss-120b
88.9
SimpleBench
GPT-5 leads by +41.5
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5
48.0
gpt-oss-120b
6.5
SimpleQA Verified
GPT-5 leads by +36.7
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5
50.6
gpt-oss-120b
13.9
SWE-Bench Verified (Bash Only)
GPT-5 leads by +39.0
SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks.
GPT-5
65.0
gpt-oss-120b
26.0
Terminal Bench
GPT-5 leads by +30.9
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency.
GPT-5
49.6
gpt-oss-120b
18.7
WeirdML
GPT-5 leads by +12.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5
60.7
gpt-oss-120b
48.2
Full benchmark table
BenchmarkGPT-5gpt-oss-120b
Aider polyglot
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
88.041.8
APEX-Agents
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
18.34.7
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
37.015.8
Dtbench
84.560.5
Fiction.LiveBench
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
97.244.4
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
85.067.7
HELM · GPQA
79.168.4
HELM · IFEval
87.583.6
HELM · MMLU-Pro
86.379.5
HELM · Omni-MATH
64.768.8
HELM · WildBench
85.784.5
Lech Mazur Writing
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
86.077.3
Lmca
47.026.1
Metr Time Horizons
69.656.6
Mystery Game Puzzles
15.20.0
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
91.488.9
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
48.06.5
SimpleQA Verified
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
50.613.9
SWE-Bench Verified (Bash Only)
SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks.
65.026.0
Terminal Bench
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency.
49.618.7
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
60.748.2
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-5$1.25$10.00400K tokens (~200 books)$34.38
OpenAI logogpt-oss-120b$0.09$0.36131K tokens (~66 books)$1.57
GPT-5 leads on 20 of 21 shared benchmarks (Aider polyglot, APEX-Agents, Chess Puzzles, Dtbench, 16 more), gpt-oss-120b on 1 (HELM · Omni-MATH)