GPT-5
Aug 2025
GPT-5Compare inon
Benchmarks of GPT-566
BenchmarkByScoreRank
Overall1
Knowledge4
Reasoning4
Math15
Science2
Coding4
Agents2
Multimodal2
Writing15
Health & law3
Documents1
Legacy · saturated or no longer reported13
No benchmark matches
Rankingat high effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGLM 5.2maxOpen+17%-37%$1.47No image input
BetterMiMo v2.5thinkingOpen+7%-95%$0.019CheaperGLM 4.7 FlashthinkingOpen+17%-96%$0.061 / $0.40Context: 400K → 200K+1
CheaperStep 3.7 FlashhighOpen+16%-87%$0.20 / $1.15Context: 400K → 256KCheaperGLM 5 Turbothinking+16%-45%$1.20 / $4Context: 400K → 203K+1ModelScoreCostPer taskWhat changes
GLM 5.2maxOpen+17%-37%$1.47No image inputGLM 4.7 FlashthinkingOpen+17%-96%$0.061 / $0.40Context: 400K → 200K+1Step 3.7 FlashhighOpen+16%-87%$0.20 / $1.15Context: 400K → 256KGLM 5 Turbothinking+16%-45%$1.20 / $4Context: 400K → 203K+1GLM 5V Turbothinking+16%-45%$1.20 / $4Context: 400K → 203KModelScoreCostPer taskWhat changes
MiMo v2.5thinkingOpen+7%-95%$0.019MiMo v2.5 ProthinkingOpen+11%-84%$0.054No image inputaTrinity Large ThinkingthinkingOpen+6%-89%$0.12Context: 400K → 262K+2
Grok 4.3high+15%-55%$0.21
Qwen 3.5 9BthinkingOpen+2%-97%$0.21Context: 400K → 262KModelScoreCostPer taskWhat changes
GLM 5.2maxOpen+17%-37%$1.47No image inputGLM 4.7 FlashthinkingOpen+17%-96%$0.061 / $0.40Context: 400K → 200K+1Step 3.7 FlashhighOpen+16%-87%$0.20 / $1.15Context: 400K → 256KGLM 5thinkingOpen+16%-55%$1 / $3.20Context: 400K → 203K+1GLM 5.1thinkingOpen+15%-37%$1.02Context: 400K → 203K+1ModelScoreCostPer taskWhat changes
GPT-5.5high+10%—$1.54Prompts with >272K input tokensGPT-5.3 Codexxhigh+1%—$1.75 / $14DeprecatedGPT-5.6 Solhigh-2%—$0.81GPT-5.1high-3%—$1.25 / $10o3thinking-5%—$2 / $8Context: 400K → 200KGPT-5.6 Terrahigh-8%—$0.34Prompts with >272K input tokensGPT-5.2medium-12%—$1.75 / $14GPT-5 Minihigh-19%—$0.053All OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam28.5#88
Arena Text · overall1,435#70
Arena Text · Chinese1,421.8#95
Arena Text · English1,409.1#92
Arena Text · French1,407.6#87
Arena Text · German1,416.3#63
Arena Text · Japanese1,401.6#43
Arena Text · Korean1,357.4#74
Arena Text · non-English1,396.9#84
Arena Text · Polish1,411.5#62
Arena Text · Russian1,401.9#79
Arena Text · Spanish1,387.6#94
AA Omniscience Index-8.7#89
CritPt (physics)5.7#75
AA Omniscience · Accuracy40.3#46
AA-LCR (long context) 1.178.2#67
MathArena · BRUMO 202591.7#12
MathArena · CMIMC 202588.8#8
MathArena · IMO 202538.1#1
MMLU-Pro · official boardlab87.1
HealthBench Professional length-adjustedlab46.2
AIME 2025lab94.6
HMMT February 2025lab88.3
HMMT November 2025lab89.2
IMOAnswerBenchlab76
HMMT 2025 chart edition unstatedlab88.3
Arena Text · overall · full cohort1,406.2#87
GPQA Diamond85.4#79
AIME 2025 · AA archived94.3#7
Coding
Terminal Bench 2.0lab35.2
LiveCodeBenchlab84.5
Codeforces Ratinglab2,537
SWE Verifiedlab74.9
Terminal-Bench 2.135.2#92
Aider Polyglot · two attempts88#1
Agents & Tool Use
GDPval-AA (work tasks) 2.120.9#90
τ³-Banking · AA22.1#48
Tau2-Benchlab80.2
MCP-Universelab47.9
MCP-Marklab50.9
Tool-Decathlonlab29
HLE without toolslab26.3
τ²-bench · AA84.8#64
Writing & Language
Arena Text · creative writing1,372#87
IFBench (instructions)73.1#33
Vision & Documents
MMMU-Pro (vision)74.2#56
Arena Vision · overall1,208.2#62
FAQ
How much does GPT-5 cost?›
$1.25 per 1M input tokens and $10 per 1M output tokens; cached input $0.13 per 1M.
Is GPT-5 free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How good is GPT-5, and what is it best at?›
#88 of 334 in Chat & Knowledge, #8 of 19 in Coding, #90 of 175 in Agents & Tool Use, #87 of 195 in Writing & Language, #56 of 124 in Vision & Documents. Strongest at: Long context, Instructions.
Is GPT-5 better than Qwen 3.5 9B?›
On τ²-bench · AA, GPT-5 scores 86.5 vs 86.8 — about the same.
How can I use GPT-5?›
Through the API of Azure, OpenAI.
What is the context window of GPT-5?›
400K tokens, with up to 128K output tokens.
When was GPT-5 released? Is there a newer version?›
Released 2025-08-07. It has been superseded by GPT-5.1.
Is GPT-5 open source?›
No, GPT-5 is a closed model available through an API. The closest open-weights option here is GLM 5.2.
Can GPT-5 read images?›
It accepts text and images, PDF files as input.
What is GPT-5?›
GPT-5 is a closed language model from OpenAI, released Aug 2025, the successor to o3 Pro.
What are the best alternatives to GPT-5?›
GLM 5.2 (cheaper), MiMo v2.5 (better).