GPT-5 (2025-08-07)
Aug 2025
GPT-5 (2025-08-07)Compare inon
Benchmarks of GPT-5 (2025-08-07)21
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math5Leads on 1
Agents1
Writing2
Legacy · saturated or no longer reported10
No benchmark matches
Rankingat medium effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMuse Sparkunstated+43%-42%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1
BetterClaude Opus 4.8max+73%+191%$4.08
OpenKimi K2.6unstated+43%-50%$0.95 / $4Context: 400K → 256K
CheaperGemini 3 Flash Previewunstated+31%-67%$0.50 / $3
CheaperGLM 5.1unstatedOpen+23%-37%$1.40 / $4.40Context: 400K → 203K+1ModelScoreCostPer taskWhat changes
Muse Sparkunstated+43%-42%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1Kimi K2.6unstatedOpen+43%-50%$0.95 / $4Context: 400K → 256KGemini 3 Flash Previewunstated+31%-67%$0.50 / $3GLM 5.1unstatedOpen+23%-37%$1.40 / $4.40Context: 400K → 203K+1GPT-5.4 Mini (2026-03-17)high+4%-51%$0.75 / $4.50ModelScoreCostPer taskWhat changes
Claude Opus 4.8max+73%+191%$4.08GPT-5.4 Pro (2026-03-05)+84%+1,864%$30 / $180No strict JSONGPT-5.4 (2026-03-05)xhigh+75%+64%$2.50 / $15Claude Opus 4.7xhigh+61%+191%$5 / $25Claude Opus 4.6max+49%+191%$5 / $25ModelScoreCostPer taskWhat changes
Kimi K2.6unstatedOpen+43%-50%$0.95 / $4Context: 400K → 256KGLM 5.1unstatedOpen+23%-37%$1.40 / $4.40Context: 400K → 203K+1Kimi K2 ThinkingunstatedOpen-21%-75%$0.47 / $2Context: 400K → 256K+1GLM 5unstatedOpen-40%-55%$1 / $3.20Context: 400K → 203K+1
Qwen3 235B A22B Thinking 2507unstatedOpen-69%-78%$0.23 / $2.30Context: 400K → 262K+2ModelScoreCostPer taskWhat changes
GPT-5.4 Pro (2026-03-05)+84%—$30 / $180No strict JSONGPT-5.4 (2026-03-05)xhigh+75%—$2.50 / $15GPT-5.2 (2025-12-11)medium+35%—$1.75 / $14GPT-5.4 Mini (2026-03-17)high+4%—$0.75 / $4.50GPT-5.1 (2025-11-13)mediumsame—$1.25 / $10GPT-5.4 Nano (2026-03-17)high-5%—$0.20 / $1.25GPT-5 Mini (2025-08-07)medium-25%—$0.25 / $2o3 (2025-04-16)medium-38%—$2 / $8Context: 400K → 200KAll OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
MATH Level 597.9#1
FrontierMath27.2#14
FrontierMath Tier 46.3#13
Chess Puzzles32#41
Mystery Game Puzzles15#49
GPQA Diamond · Epoch85.4#54
OTIS Mock AIME 2024 202587.2#54
Coding
SWE-rebench · all · 2025-07-01 to 2025-12-0144#1
SWE-rebench · Go · 2025-07-01 to 2025-12-010#1
SWE-rebench · Java · 2025-07-01 to 2025-12-010#1
SWE-rebench · Rust · 2025-07-01 to 2025-12-010#1
SWE-rebench · Python · 2025-07-01 to 2025-12-0144#1
SWE-rebench · TypeScript · 2025-07-01 to 2025-12-010#1
SWE-bench Verified · Epoch71.5#17
FAQ
How much does GPT-5 (2025-08-07) cost?›
$1.25 per 1M input tokens and $10 per 1M output tokens.
Is GPT-5 (2025-08-07) free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How good is GPT-5 (2025-08-07), and what is it best at?›
#28 of 83 in Chat & Knowledge, #8 of 19 in Coding, #19 of 24 in Agents & Tool Use, #33 of 95 in Writing & Language.
Is GPT-5 (2025-08-07) better than GLM 5.1?›
On FrontierMath, GPT-5 (2025-08-07) scores 32.4 vs 33.4 — lower.
How can I use GPT-5 (2025-08-07)?›
Through the OpenAI API.
What is the context window of GPT-5 (2025-08-07)?›
400K tokens.
When was GPT-5 (2025-08-07) released? Is there a newer version?›
Released 2025-08-07. It has been superseded by GPT-5.6 Sol.
Can GPT-5 (2025-08-07) read images?›
It accepts text and images as input.
What is GPT-5 (2025-08-07)?›
GPT-5 (2025-08-07) is a language model from OpenAI, released Aug 2025.
What are the best alternatives to GPT-5 (2025-08-07)?›
Muse Spark (cheaper), Claude Opus 4.8 (better), Kimi K2.6 (open weights).