T2LSC-Bench
Models render text at a specified location in an image. Judges check the lettering and whether its meaning alters other objects or the background.
- Made by
- Yan Wang and colleagues
- Released
- September 2026
- Kind
- Image generation and editing
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Image, video and 3D generation
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.1 Flash Image leads with 99% among models released by February 2026 Gemini 3.1 Flash Image leads with 99% among models released by February 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3.1 Flash Image 99%
- 2 Qwen-2.0 98.8%
- 3 GPT-Image-1.5 98.3%
- 4 Seedream 5.0 97.1%
- 5
Wan 2.6 Image 94.2%
- 6
Gemini 2.5 Flash Image Preview (nano-banana) 59.2%
Source: The T2LSC-Bench paper
- 1
Gemini 3.1 Flash Image 99%
- 2 GPT-Image-1.5 98.3%
- 3
Wan 2.6 Image 94.2%
- 4
Gemini 2.5 Flash Image Preview (nano-banana) 59.2%
Source: The T2LSC-Bench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 99% | Feb 2026 | Official leaderboard | |
| 2 | Qwen-2.0 | 98.8% | Official leaderboard | ||
| 3 | GPT-Image-1.5 | 98.3% | Official leaderboard | ||
| 4 | Seedream 5.0 | 97.1% | Official leaderboard | ||
| 5 | | 94.2% | Official leaderboard | ||
| 6 | | 59.2% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 99% | Feb 2026 | Official leaderboard | |
| 2 | GPT-Image-1.5 | 98.3% | Official leaderboard | ||
| 3 | | 94.2% | Official leaderboard | ||
| 4 | | 59.2% | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as Subject preservation, Aligned SLR and Conflicting SLR. Gemini 3.1 Flash Image leads 4 of them, and GPT-Image-1.5 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Subject preservation
4 models we track have a score here.
- 1
Gemini 3.1 Flash Image 98.8%
- 2 GPT-Image-1.5 96.9%
- 3
Gemini 2.5 Flash Image Preview (nano-banana) ↑1 96.7%
- 4
Wan 2.6 Image ↓1 91.7%
Aligned SLR
4 models we track have a score here.
- 1 GPT-Image-1.5 ↑1 0.50%
- 2
Gemini 3.1 Flash Image ↓1 0.50%
- 3
Gemini 2.5 Flash Image Preview (nano-banana) ↑1 1.00%
- 4
Wan 2.6 Image ↓1 2.00%
Conflicting SLR
4 models we track have a score here.
- 1
Gemini 3.1 Flash Image 13%
- 2 GPT-Image-1.5 14%
- 3
Gemini 2.5 Flash Image Preview (nano-banana) ↑1 21.9%
- 4
Wan 2.6 Image ↓1 22.4%
Aligned conditional SLR
4 models we track have a score here.
- 1 GPT-Image-1.5 ↑1 0.50%
- 2
Gemini 3.1 Flash Image ↓1 0.50%
- 3
Gemini 2.5 Flash Image Preview (nano-banana) ↑1 1.30%
- 4
Wan 2.6 Image ↓1 2.10%
Conflicting conditional SLR
4 models we track have a score here.
- 1
Gemini 3.1 Flash Image 13.1%
- 2 GPT-Image-1.5 14.2%
- 3
Gemini 2.5 Flash Image Preview (nano-banana) ↑1 22.7%
- 4
Wan 2.6 Image ↓1 23.4%
SLR difference
Percentage-point difference between conflicting and aligned conditions. 4 models we track have a score here.
- 1
Gemini 3.1 Flash Image 12.5%
- 2 GPT-Image-1.5 13.5%
- 3
Wan 2.6 Image 20.4%
- 4
Gemini 2.5 Flash Image Preview (nano-banana) 20.9%
Gemini 3.1 Flash Image on the official leaderboard passed 85% in February 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official T2LSC-Bench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 4 models we track, plus 2 other entries on its leaderboard.
- Note Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Flash Image. That’s expected for a saturated test.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Saturated. The best is 99%, past 85% since February 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 4 rows for models we track and 2 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.