Skip to main content
BenchLM
Data

EyeBench v3: a vision exam for frontier models (EyeBench)

We show this table for reference; we do not rank on it.

Data verified

Adonis Singh's visual reasoning benchmark: 100 generated images, each with one question whose answer is a single number. Models count the differences between two nearly identical panels, count closed loops in a tangle of curves, count the connected parts of a graph drawing, pick the tile that completes a 4x4 pattern, and count the turns along a maze path. Scoring is exact match.

Accuracy on EyeBench — EyeBench data of November 18, 2026

We mirror the published accuracy view for EyeBench. GPT-6.2 Astra leads the public snapshot at 99%, followed by GPT-6.2 Sol (98%) and GPT-6 Astra (95%). We do not use these results to rank models overall.

33 modelsMultimodal & GroundedCurrentDisplay onlyUpdated EyeBench data of November 18, 2026

Accuracy table (33 models)

Accuracy results for EyeBench
RankModel / configurationScoreParameters (B)Open / closed
1GPT-6.2 AstraOpenAImax reasoning99/100 correct (±1.0) · $19.17 for the run
99%
Not reportedClosed
2GPT-6.2 SolOpenAImax reasoning98/100 correct (±1.4) · $5.02 for the run
98%
Not reportedClosed
3GPT-6 AstraOpenAImax reasoning95/100 correct (±2.2) · $25.71 for the run
95%
Not reportedClosed
4GPT-6.1 TerraOpenAImax reasoning94/100 correct (±2.4) · $7.03 for the run
94%
Not reportedClosed
5GPT-6.1 SolOpenAImax reasoning93/100 correct (±2.5) · $6.25 for the run
93%
Not reportedClosed
6Claude Fable 5.2Anthropicmax reasoning86/100 correct (±3.5) · 1 unanswered · $65.56 for the run
86%
Not reportedClosed
7Claude Opus 5.5Anthropicmax reasoning78/100 correct (±4.1) · $47.94 for the run
78%
Not reportedClosed
8Claude Sonnet 5.5Anthropicmax reasoning71/100 correct (±4.5) · 2 unanswered · $41.43 for the run
71%
Not reportedClosed
9Gemini 4 ArgonGooglehigh reasoning66/100 correct (±4.7) · $23.75 for the run
66%
Not reportedClosed
10GPT-6 SolOpenAImax reasoning59/100 correct (±4.9) · $7.89 for the run
59%
Not reportedClosed
11GPT-5.6 SolOpenAImax reasoning58/100 correct (±4.9) · 8 unanswered · $54.79 for the run
58%
Not reportedClosed
12Claude Haiku 5.5Anthropicmax reasoning50/100 correct (±5.0) · 19 unanswered · $2.73 for the run
50%
Not reportedClosed
13GPT-5.6 TerraOpenAImax reasoning42/100 correct (±4.9) · 1 unanswered · $44.80 for the run
42%
Not reportedClosed
14GPT-5.5OpenAIxhigh reasoning41/100 correct (±4.9) · $44.65 for the run
41%
Not reportedClosed
15GPT-5.5 ProOpenAImedium reasoning41/100 correct (±4.9) · $243.56 for the run
41%
Not reportedClosed
16Claude Fable 5.1Anthropicmax reasoning40/100 correct (±4.9) · 5 unanswered · $165.97 for the run
40%
Not reportedClosed
17Qwen3.8 MaxAlibabaxhigh reasoning39/100 correct (±4.9) · $4.88 for the run
39%
Not reportedOpen
18Muse Spark 1.3Metaxhigh reasoning37/100 correct (±4.8) · 23 unanswered · $4.22 for the run
37%
Not reportedClosed
19Muse Spark 1.2Metaxhigh reasoning34/100 correct (±4.7) · $8.69 for the run
34%
Not reportedClosed
20Gemini 3.8 FlashGooglehigh reasoning31/100 correct (±4.6) · $9.87 for the run
31%
Not reportedClosed
21GPT-5.6 LunaOpenAImax reasoning30/100 correct (±4.6) · 3 unanswered · $4.19 for the run
30%
Not reportedClosed
22GPT-6 LunaOpenAImax reasoning30/100 correct (±4.6) · 1 unanswered · $0.53 for the run
30%
Not reportedClosed
23Kimi K3Moonshot AImax reasoning29/100 correct (±4.5) · 18 unanswered · $25.66 for the run
29%
Not reportedOpen
24Gemini 3.1 ProGooglehigh reasoning28/100 correct (±4.5) · 3 unanswered · $21.88 for the run
28%
Not reportedClosed
25Claude Fable 5Anthropicmax reasoning27/100 correct (±4.4) · $24.87 for the run
27%
Not reportedClosed
26Gemini 3.7 FlashGooglehigh reasoning27/100 correct (±4.4) · $3.27 for the run
27%
Not reportedClosed
27Claude Opus 5Anthropicmax reasoning26/100 correct (±4.4) · 1 unanswered · $24.15 for the run
26%
Not reportedClosed
28Claude Sonnet 5Anthropicmax reasoning21/100 correct (±4.1) · 1 unanswered · $11.45 for the run
21%
Not reportedClosed
29GLM-5.3-FlashZ.AImax reasoning21/100 correct (±4.1) · 5 unanswered · $0.31 for the run
21%
Not reportedOpen
30Grok 4.6xAIxhigh reasoning19/100 correct (±3.9) · $0.92 for the run
19%
Not reportedClosed
31Mistral Large 4Mistralnone reasoning15/100 correct (±3.6) · 7 unanswered · $3.97 for the run
15%
Not reportedOpen
32DeepSeek V4 Flash Vision ExpDeepSeekmax reasoning13/100 correct (±3.4) · $1.42 for the run
13%
Not reportedUnknown
33InklingThinking Machines Labxhigh reasoning9/100 correct (±2.9) · $2.31 for the run
9%
Not reportedOpen

How to read this leaderboard

Higher is better. GPT-6.2 Astra leads with 99 of 100, ahead of GPT-6.2 Sol (98), GPT-6 Astra (95), GPT-6.1 Terra (94) and GPT-6.1 Sol (93). The best model from another lab is Claude Fable 5.2 at 86, then Claude Opus 5.5 at 78 and Gemini 4 Argon at 66. Spot the difference separates the field most: only the two GPT-6.2 models reach 90% on it, while Fable 5.2 gets 50%. Gemini 4 Argon is perfect on graphs and patterns but solves 15% of mazes. Cost varies widely for similar scores: GPT-6.2 Sol's run cost about $5, against $19 for GPT-6.2 Astra and $66 for Fable 5.2.

Operator receipt: 33 sourced rows are currently displayable on this page; the leading published row is GPT-6.2 Astra at 99%.

Honest limit: One hundred questions in five task types is a small test: one question is a point of accuracy, and the standard error near the middle of the scale is about 5 points. The images are synthetic puzzles, so the benchmark measures fine-grained counting and tracing, not photos, documents or charts. Each model is shown at its highest measured reasoning effort, and effort names are set by each provider, so they do not line up across vendors. Failed requests count as wrong, so an API outage during a run lowers a score. EyeBench is a one-person project; its questions are not published, and BenchLM cannot re-run them. BenchLM shows EyeBench as display only; it does not enter overall or category rankings.

How EyeBench is shown here

We mirror the EyeBench v3 leaderboard by Adonis Singh. Each model gets 100 generated images, 20 in each of 5 task types: count the differences between two nearly identical panels, count closed loops in a tangle of curves, count the connected parts of a graph drawing, pick the tile that completes a 4x4 pattern, and count the turns along a maze path. Every answer is a single number, marked right or wrong.

A question with no parsed answer, an invalid output or a failed request counts as wrong. Each model is listed once, at the highest reasoning effort it was run at, as on the source board. Effort names are set by each provider and do not line up across vendors. Cost is the run's tokens at the model's API prices. EyeBench is display only on BenchLM.

Snapshot

33 models100 questions5 task typesExact matchDisplay only

The published EyeBench snapshot places GPT-6.2 Astra first at 99%. The third row is 4 points behind. The broader top-10 range is 40 points, so the table still separates the published systems.

33 models have been evaluated on EyeBench. The benchmark falls in the Multimodal & Grounded category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. EyeBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About EyeBench

Year

2026

Tasks

100 generated images in five task types: spot the difference, closed loops, graph components, 4x4 pattern completion and maze turns (20 each)

Format

One image and one question per request; the answer is a single integer

Difficulty

Counting and tracing fine visual detail exactly: small differences between panels, crossing curves and long maze paths

EyeBench v3 has 100 procedurally generated images, 20 in each of five task types: spot the difference (count the differences between two nearly identical panels), topology (count closed loops in a tangle of curves), graph (count connected components in a graph drawing), pattern (pick the option that completes a 4x4 visual matrix) and maze (count the turns along a path). Each question is one request with one image, and the answer must be a single integer. Scoring is exact match; on four pattern items the correct tile is pixel-identical to another option, and either is accepted. A question with no parsed answer, an invalid output or a failed request counts as wrong. The publisher runs each model at several reasoning efforts and lists it at the highest one measured; BenchLM shows that same run, once per model. Costs are the run's tokens at the model's API prices; caching does not apply, since every question is a single request. BenchLM reads the run-level data the EyeBench site publishes and keeps each task type's accuracy in its history.

Freshness and provenance

Version

EyeBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does EyeBench measure?

Whether a model can read fine visual detail exactly. Each of 100 generated images comes with one question whose answer is a number: how many differences between two panels, how many closed loops, how many connected parts of a graph, which tile completes a pattern, or how many turns a maze path takes. Only the exact number counts.

Which model leads EyeBench?

GPT-6.2 Astra at max reasoning leads with 99 of 100, followed by GPT-6.2 Sol (98), GPT-6 Astra (95) and GPT-6.1 Terra (94). The best non-OpenAI model is Claude Fable 5.2 at 86 (EyeBench data of November 18, 2026).

Why does BenchLM show one effort level per model on EyeBench?

EyeBench runs many models at several reasoning efforts, and its leaderboard lists each model at the highest effort measured. BenchLM shows the same run, so every model appears once.

Last updated: EyeBench data of November 18, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 7,000+ subscribers.

One email each week. Unsubscribe anytime.