OpenAIUnited States· released Nov 2025

GPT-5.1

Name: GPT-5.1
Author: OpenAI

Ranked #32, 46.0% behind the frontier on average.

OpenAI, United States. One of 26 models from this lab on the Index.

Third-party publishedMedium confidence (7+ comparable tests, 3+ Index categories)

Snapshot September 8, 2026

OpenCharts Index

54.0

Ranked #32 (31 to 32) of 36 · 46.0% behind the frontier on average · 18 comparable tests · 3 counting categories

Drop any single test and the Index lands between 51.5 and 56.4, anywhere from #31 to #32. Neighbours inside that range are ties.

4 of 8 hardest tests · share of the frontier

Distance to today's frontier on the hardest tests. Not a measure of intelligence.

What it's known for

GPT-5.1, in 18 results.

Strongest in coding (58.6) and reasoning (52.0). It trails the frontier most in agentic, 48.7% behind on average. No comparable result yet in long context. Between 40% and 50% behind the best published results, on average. Drop any single test and it would sit anywhere from #31 to #32.

Strongest category

Coding

Writing, fixing and shipping real code, judged by tests or users.

58.6

SWE-bench Verified68.0% · 81% of best
SciCode43.3% · 70% of best
WeirdML60.8% · 65% of best
Code Arena (WebDev)1,392 · 18% win rate vs leader

Mean of 4 of the category's 7 comparable tests. Counts toward the Index.

Best single result

Mock AIME 2024–2025

Solve competition mathematics problems that have a single exact integer answer.

88.6%

88.6% of the best (100.0%) · #46 of 78.

Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.

Where it trails

CritPt

Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.

4.9%

85.0% behind the best published result (32.3%) · #45 of 78.

Research physics is far past textbook recall. Only a few models produce anything a physicist would accept.

Not measured yet

No comparable result yet in this category. A blank is a blank, never a zero, and it does not lower the Index.

Long context

Covered, but not averaged into the Index:

Knowledgesingle-test category, shown beside the Index · 63.5
Math1 of 5 tests · needs 3 · mean 88.6
Multimodalsingle-test category, shown beside the Index · 82.0
Human preferencesingle-test category, shown beside the Index · 85.1

Every score, with its source

See it at work

What GPT-5.1 was asked to do, and how it did.

Every test it has taken, by category, with the kind of task it faced, who produced the number and where the result landed against the best published one. The examples are original and illustrative, never items from the datasets themselves.

Math · mean 88.6 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)

Mock AIME 2024–2025Epoch-run

Solve competition mathematics problems that have a single exact integer answer.

88.6%

88.6% of the best (100.0%)
#46 of 78 · n = 45

2025-11-13 · high

45 problems: one problem is 2.2 points, so gaps of a few points are within noise.

Source: Epoch AI (internal runs)

Every result is read against the best published one on its test: percent scores as a share of the best above chance, Arena ratings as the expected win rate against the board leader, open-ended values on a log scale. Sitting a harder exam never lowers a model. Every number links to the publisher that produced it.

Head to head

GPT-5.1 against whoever you pick.

Choose a rival. Every counted test both have taken appears side by side as a share of the best published result on that test, with the category means above. A win is a higher share; a gap under 2 points is a tie, because one item on a 45-problem exam is 2.2 points and publishers' own standard errors are of that order.

GPT-5.1

#32·Index 54.0C-

0 : 10

wins · 0 ties · 10 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 10 of the 10 tests both have taken.

Category means

Reasoning
52.0
99.6
Knowledge
63.5
100.0
Coding
58.6
97.7
Math
88.6
99.8
Agentic
51.3
98.5
Multimodal
82.0
—
Human preference
85.1
—

Shared tests · biggest gaps first

CritPtReasoning
4.9%
31.7%
−83.2
Code Arena (WebDev)Coding
1,392
1,797
−82.3
ARC-AGI-2Reasoning
17.6%
95.0%
−81.4
APEX-AgentsAgentic
17.5%
46.7%
−61.6
SimpleQA VerifiedKnowledge
48.0%
75.6%
−36.5
WeirdMLCoding
60.8%
92.9%
−34.6
ARC-AGI-1Reasoning
72.8%
98.5%
−26.1
SciCodeCoding
43.3%
56.5%
−21.2
GPQA DiamondReasoning
87.6%
95.8%
−11.5
Mock AIME 2024–2025Math
88.6%
100.0%
−11.4

Bars are distances to the best published result on each test (percent scores above chance, Arena ratings as win rate against the leader, open-ended values on a log scale). Raw values as the publishers report them.

Open GPT-6 Astra

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted.

Category means

Reasoning52.0 · 6/6
Knowledgebeside63.5 · 1/1
Coding58.6 · 4/7
Math88.6 · 1/5
Agentic51.3 · 4/8
Multimodalbeside82.0 · 1/1
Human preferencebeside85.1 · 1/1
Long context—

Mean · tests taken of the category's comparable tests. A faded category either rests on fewer than half of them or is a single-test category (marked “beside”), which is shown next to the Index and never averaged into it.

GPQA DiamondEpoch-runReasoning

87.6%

88.5% of the best (95.8%), above chance
45th percentile of 78 · n = 198

2025-11-13 · high

GPT-5.1

GPT-5.1, in 18 results.

What GPT-5.1 was asked to do, and how it did.

GPT-5.1 against whoever you pick.

Every test, every source

Compare with its neighbours.

The best models, ranked here, working inside Theo.