GPT-5 Mini

Released	2025-08-07
Price per 1M	$0.25 in · $2.00 out
Overall score	48.0 · rank 129
Context window	400,000 tokens
Provider	OpenAI
Weights	Proprietary

Scores

Dimension	Score	Rank	Benchmarks
Overall: Balanced	48.0	129	29
Overall: Coding	47.6	125	15
Overall: Reasoning	50.8	109	16
Overall: Agentic work	45.1	156	14
Overall: Frontend	46.1	127	7
Coding	50.6	114	3
Agents	41.7	152	3
Reasoning	49.6	119	8
Math	54.0	79	5
Knowledge	47.8	105	3
Frontend	43.4	101	1
General	47.6	130	3
Multimodal	48.5	77	3
Value vs price	+1.3	110

Configurations

Configuration	Balanced	Benchmarks
Unspecified setting	46.1 ±3.4	10
High	49.1 ±2.4	21
Low	48.0 ±5.5	4
Medium	48.8 ±2.2	11
Minimal	43.1 ±5.3	7

Evidence

Coding 50.6 ±5.1

Benchmark	Result	Source	Date
SciCode	39.2%	Epoch AI	2026-11-11
LiveCodeBench (Vals run)	86.6%	Vals AI	2026-09-01
SWE-bench Verified (Epoch run)	64.7%	Epoch AI	2026-02-01
SWE-bench Verified (Vals run)	60.8%	Vals AI	2026-09-01

Agents 41.7 ±9.7

Benchmark	Result	Source	Date
Terminal-Bench 2.0	34.8%	Epoch AI	2025-08-07
BFCL v4	55.5%	BFCL	2026-04-12
Vending-Bench 2	$-31	Epoch AI	2026-11-11

Reasoning 49.6 ±2.2

Benchmark	Result	Source	Date
ARC-AGI-2	4.4%	Epoch AI	2026-11-11
ARC-AGI-2 (ARC Prize verified)	4.4%	ARC Prize	2026-11-11
CritPt	0.0%	Epoch AI	2026-11-11
ARC-AGI-1 (ARC Prize verified)	54.3%	ARC Prize	2026-11-11
ARC-AGI-1	54.3%	Epoch AI	2026-11-11
EnigmaEval	8.2%	Epoch AI	2026-11-11
GPQA Diamond	75.0%	Epoch AI	2025-10-30
GPQA Diamond (Vals run)	80.3%	Vals AI	2026-09-01
Kagi Reasoning Benchmark	70.3%	Kagi	2026-11-11
Chess Puzzles	24.0%	Epoch AI	2026-10-13
Mystery Game Puzzles	10.0%	Epoch AI	2026-08-27

Math 54.0 ±1.1

Benchmark	Result	Source	Date
FrontierMath Tiers 1-3	46.7%	Epoch AI	2026-06-12
MATH Level 5	97.9%	Epoch AI	2025-10-30
FrontierMath Tier 4	12.2%	Epoch AI	2026-06-12
ProofBench	9.0%	Epoch AI	2026-11-11
OTIS Mock AIME 2024-2025	86.7%	Epoch AI	2025-10-30
FrontierMath Tiers 1-3 (2025 set)	27.2%	Epoch AI	2025-11-13
FrontierMath Tier 4 (2025 set)	6.3%	Epoch AI	2025-10-30

Knowledge 47.8 ±2.8

Benchmark	Result	Source	Date
SimpleQA Verified	21.6%	Epoch AI	2026-08-10
Humanity's Last Exam	19.4%	Epoch AI	2026-11-11
MMLU-Pro (Vals run)	82.2%	Vals AI	2026-09-01

Frontend 43.4 ±0.8

Benchmark	Result	Source	Date
Vibe Code Bench v1.1	14.2%	Vals AI	2026-11-09

General 47.6 ±3.2

Benchmark	Result	Source	Date
LMArena Text	1,390	LMArena	2026-11-09
EQ-Bench Creative Writing v3	1,314	EQ-Bench	2026-11-11
EQ-Bench Longform Creative Writing	56.2%	EQ-Bench	2026-11-11

Multimodal 48.5 ±2.9

Benchmark	Result	Source	Date
LMArena Vision	1,185	LMArena	2026-11-09
MMMU-Pro (Vals run)	78.9%	Vals AI	2026-09-01
VPCT	40.2%	Epoch AI	2026-11-11

Results not used in the score

Benchmark	Result	Source	Why not used
ARC-AGI-1	5.3%	Epoch AI	A stronger configuration result was used
ARC-AGI-1	37.3%	Epoch AI	A stronger configuration result was used
ARC-AGI-1	26.3%	Epoch AI	A stronger configuration result was used
ARC-AGI-1 (ARC Prize verified)	5.3%	ARC Prize	A stronger configuration result was used
ARC-AGI-1 (ARC Prize verified)	37.3%	ARC Prize	A stronger configuration result was used
ARC-AGI-1 (ARC Prize verified)	26.3%	ARC Prize	A stronger configuration result was used
ARC-AGI-2	1.7%	Epoch AI	A stronger configuration result was used
ARC-AGI-2	4.0%	Epoch AI	A stronger configuration result was used
ARC-AGI-2	0.8%	Epoch AI	A stronger configuration result was used
ARC-AGI-2 (ARC Prize verified)	1.7%	ARC Prize	A stronger configuration result was used
ARC-AGI-2 (ARC Prize verified)	4.0%	ARC Prize	A stronger configuration result was used
ARC-AGI-2 (ARC Prize verified)	0.8%	ARC Prize	A stronger configuration result was used
BFCL v4	27.8%	BFCL	A stronger configuration result was used
Chess Puzzles	0.0%	Epoch AI	A stronger configuration result was used
Chess Puzzles	16.0%	Epoch AI	A stronger configuration result was used
CritPt	0.0%	Epoch AI	A stronger configuration result was used
FrontierMath Tier 4 (2025 set)	4.2%	Epoch AI	A stronger configuration result was used
FrontierMath Tiers 1-3	6.0%	Epoch AI	A stronger configuration result was used
FrontierMath Tiers 1-3	18.3%	Epoch AI	A stronger configuration result was used
FrontierMath Tiers 1-3 (2025 set)	20.3%	Epoch AI	A stronger configuration result was used
GPQA Diamond	71.7%	Epoch AI	A stronger configuration result was used
GPQA Diamond	71.7%	Epoch AI	A stronger configuration result was used
MATH Level 5	96.8%	Epoch AI	A stronger configuration result was used
Mystery Game Puzzles	5.0%	Epoch AI	A stronger configuration result was used
Mystery Game Puzzles	4.0%	Epoch AI	A stronger configuration result was used
OTIS Mock AIME 2024-2025	55.6%	Epoch AI	A stronger configuration result was used
OTIS Mock AIME 2024-2025	78.3%	Epoch AI	A stronger configuration result was used
SciCode	39.0%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	34.8%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	31.9%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	29.2%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	24.0%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	22.3%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	31.9%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	29.2%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	24.0%	Epoch AI	A stronger configuration result was used
Terminal-Bench 2.0	22.2%	Epoch AI	A stronger configuration result was used
VPCT	39.0%	Epoch AI	A stronger configuration result was used

Names matched to this model

gpt-5-mini, gpt-5-mini-2025-08-07

Compare GPT-5 Mini with other models