ImageJevBench v0.1.5
Version 0.1.5
Models answer decisions about images and assign probabilities to the answers. The maker ranks capability using accuracy and calibration within cost and latency limits.
Benchmark Heaven’s archived board compares 50 systems on 228 public and 456 sealed items.
- Made by
- Benchmark Heaven
- Released
- October 2026
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- A host
- In views
- Vision
- Strongest model tested
-
Gemini 3.8 Flash #24 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Wity-1 tops the leaderboard with 80.2 GPT-6 Luna leads with 16.1 among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. The best model we track is GPT-6 Luna, at 16.1. This view shows only models we track, each at its best.
The newest model with a score here came out in September 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-6.1 Sol
- and 16 more
- 80.2 Wity-1
- 76.4 Imajev-4B
- 73.1 Jev-Omni
- 71.9 NeoHorse Jev 4B
- 69.8 Visual-Jev 4B Answer-SFT
- 69.5 JPT-4B (kirp / llm2jev)
- 68.7 imajev 2B
- 66.9 Glance (frozen Qwen3-VL-4B)
- 66.8 AutoJev-27B
- 66.8 Mapika decider-2b-vision BF16
- 65.9 jev-spatial (Fr0zencr4nE)
- 65.8 JPT-9B (kirp / llm2jev)
- 65.7 OmniJev 4B (tinnel123)
- 65.4 Reflex 4B (released stable configuration)
- 65.1 OmniJev-Qwen3.5-9B-v4 (tzcfly)
- 65.0 Jevify Gemma 4 26B-A4B
- 63.8 Surogate Rune 26B-A4B v3
- 63.8 JevAny-27B SFT
- 63.5 JevAny-27B RLCR
- 63.4 Jev-Vision 8B (SeanLiu)
- 63.2 shisa-de-1
- 62.8 OmniJev 2B (tinnel123)
- 62.6 CUA-S1 4B
- 59.8 Standard One 8B
- 59.0 Jevify Qwen3-VL-2B T2
- 58.3 imajev 9B
- 57.7 Visual-Jev generic (zero-shot Qwen3.5-4B baseline)
- 50.0 djev-distill-v4 (tarsur385)
- 49.4 djev-spark NVFP4
- 48.8 diffusiongemma-26b djev v10 step160 (snowicarus)
- 47.7 vjev-vision (yah01)
- 47.1 Autoloops – Gemma 4 31B IT
- 46.6 djev-dev BF16
- 43.6 Winnow-12B (Q8_0 + F16 vision projector)
- 30.5 JPT-0.8B (kirp / llm2jev)
- 29.8 Jevify Gemma 4 E4B
- 29.0 Standard One 3B
- 26.8 Gevva E4B (text checkpoint, image input)
- 26.8 OmniJev 0.8B (tinnel123)
- 21.9 Gevva E2B multimodal
- 21.5 JEVision (divyanshx11, visual route)
- 19.3 Bonsai-2-27B v2 PQ2_0 + Q8_0 MMProj
- 17.4 Qevi-2B (MeerDevelopment)
- 16.1 GPT-6 Luna
- 11.1 GPT-5.6 Luna
- 9.58
Gemini 3.1 Flash-Lite
- 0.11 PlayJev 0.8B
- 0.00
Gemini 3.8 Flash
- 0.00 OpenJev 4B NLI v2 (official image-premise path)
- 0.00 OpenJev 4B NLI v5
- 1 Wity-1 Wity SystemOne, reasoning=auto 80.2
- 2 Imajev-4B PyTorch; one rotation; --fast; --merge-lora; calibration.json; server 8501f5c3; adapter c9e5f132. 76.4
- 3 Jev-Omni 73.1
- 4 NeoHorse Jev 4B 71.9
- 5 Visual-Jev 4B Answer-SFT 69.8
- 6 JPT-4B (kirp / llm2jev) 69.5
- 7 imajev 2B 68.7
- 8 Glance (frozen Qwen3-VL-4B) 66.9
- 9 AutoJev-27B 66.8
- 10 Mapika decider-2b-vision BF16 66.8
- 11 jev-spatial (Fr0zencr4nE) 65.9
- 12 JPT-9B (kirp / llm2jev) 65.8
- 13 OmniJev 4B (tinnel123) 65.7
- 14 Reflex 4B (released stable configuration) 65.4
- 15 OmniJev-Qwen3.5-9B-v4 (tzcfly) 65.1
- 16 Jevify Gemma 4 26B-A4B 65.0
- 17 Surogate Rune 26B-A4B v3 63.8
- 18 JevAny-27B SFT 63.8
- 19 JevAny-27B RLCR 63.5
- 20 Jev-Vision 8B (SeanLiu) 63.4
- 21 shisa-de-1 63.2
- 22 OmniJev 2B (tinnel123) 62.8
- 23 CUA-S1 4B 62.6
- 24 Standard One 8B 59.8
- 25 Jevify Qwen3-VL-2B T2 59.0
- 26 imajev 9B 58.3
- 27 Visual-Jev generic (zero-shot Qwen3.5-4B baseline) 57.7
- 28 djev-distill-v4 (tarsur385) 50.0
- 29 djev-spark NVFP4 49.4
- 30 diffusiongemma-26b djev v10 step160 (snowicarus) 48.8
- 31 vjev-vision (yah01) 47.7
- 32 Autoloops – Gemma 4 31B IT 47.1
- 33 djev-dev BF16 46.6
- 34 Winnow-12B (Q8_0 + F16 vision projector) 43.6
- 35 JPT-0.8B (kirp / llm2jev) 30.5
- 36 Jevify Gemma 4 E4B 29.8
- 37 Standard One 3B 29.0
- 38 Gevva E4B (text checkpoint, image input) 26.8
- 39 OmniJev 0.8B (tinnel123) 26.8
- 40 Gevva E2B multimodal 21.9
- 41 JEVision (divyanshx11, visual route) 21.5
- 42 Bonsai-2-27B v2 PQ2_0 + Q8_0 MMProj 19.3
- 43 Qevi-2B (MeerDevelopment) 17.4
- 44 GPT-6 Luna OpenRouter reasoning.effort=low 16.1
- 45 GPT-5.6 Luna 11.1
- 46
Gemini 3.1 Flash-Lite 9.58
- 47 PlayJev 0.8B 0.11
- 48
Gemini 3.8 Flash 0.00
- 49 OpenJev 4B NLI v2 (official image-premise path) 0.00
- 50 OpenJev 4B NLI v5 0.00
Source: Official ImageJevBench v0.1.5 leaderboard
- 1 GPT-6 Luna OpenRouter reasoning.effort=low 16.1
- 2 GPT-5.6 Luna 11.1
- 3
Gemini 3.1 Flash-Lite 9.58
- 4
Gemini 3.8 Flash 0.00
Source: Official ImageJevBench v0.1.5 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Wity-1 | 80.2 | Wity SystemOne, reasoning=auto | Official leaderboard | |
| 2 | Imajev-4B | 76.4 | PyTorch; one rotation; --fast; --merge-lora; calibration.json; server 8501f5c3; adapter c9e5f132. | Official leaderboard | |
| 3 | Jev-Omni | 73.1 | Official leaderboard | ||
| 4 | NeoHorse Jev 4B | 71.9 | Official leaderboard | ||
| 5 | Visual-Jev 4B Answer-SFT | 69.8 | Official leaderboard | ||
| 6 | JPT-4B (kirp / llm2jev) | 69.5 | Official leaderboard | ||
| 7 | imajev 2B | 68.7 | Official leaderboard | ||
| 8 | Glance (frozen Qwen3-VL-4B) | 66.9 | Official leaderboard | ||
| 9 | AutoJev-27B | 66.8 | Official leaderboard | ||
| 10 | Mapika decider-2b-vision BF16 | 66.8 | Official leaderboard | ||
| 11 | jev-spatial (Fr0zencr4nE) | 65.9 | Official leaderboard | ||
| 12 | JPT-9B (kirp / llm2jev) | 65.8 | Official leaderboard | ||
| 13 | OmniJev 4B (tinnel123) | 65.7 | Official leaderboard | ||
| 14 | Reflex 4B (released stable configuration) | 65.4 | Official leaderboard | ||
| 15 | OmniJev-Qwen3.5-9B-v4 (tzcfly) | 65.1 | Official leaderboard | ||
| 16 | Jevify Gemma 4 26B-A4B | 65.0 | Official leaderboard | ||
| 17 | Surogate Rune 26B-A4B v3 | 63.8 | Official leaderboard | ||
| 18 | JevAny-27B SFT | 63.8 | Official leaderboard | ||
| 19 | JevAny-27B RLCR | 63.5 | Official leaderboard | ||
| 20 | Jev-Vision 8B (SeanLiu) | 63.4 | Official leaderboard | ||
| 21 | shisa-de-1 | 63.2 | Official leaderboard | ||
| 22 | OmniJev 2B (tinnel123) | 62.8 | Official leaderboard | ||
| 23 | CUA-S1 4B | 62.6 | Official leaderboard | ||
| 24 | Standard One 8B | 59.8 | Official leaderboard | ||
| 25 | Jevify Qwen3-VL-2B T2 | 59.0 | Official leaderboard | ||
| 26 | imajev 9B | 58.3 | Official leaderboard | ||
| 27 | Visual-Jev generic (zero-shot Qwen3.5-4B baseline) | 57.7 | Official leaderboard | ||
| 28 | djev-distill-v4 (tarsur385) | 50.0 | Official leaderboard | ||
| 29 | djev-spark NVFP4 | 49.4 | Official leaderboard | ||
| 30 | diffusiongemma-26b djev v10 step160 (snowicarus) | 48.8 | Official leaderboard | ||
| 31 | vjev-vision (yah01) | 47.7 | Official leaderboard | ||
| 32 | Autoloops – Gemma 4 31B IT | 47.1 | Official leaderboard | ||
| 33 | djev-dev BF16 | 46.6 | Official leaderboard | ||
| 34 | Winnow-12B (Q8_0 + F16 vision projector) | 43.6 | Official leaderboard | ||
| 35 | JPT-0.8B (kirp / llm2jev) | 30.5 | Official leaderboard | ||
| 36 | Jevify Gemma 4 E4B | 29.8 | Official leaderboard | ||
| 37 | Standard One 3B | 29.0 | Official leaderboard | ||
| 38 | Gevva E4B (text checkpoint, image input) | 26.8 | Official leaderboard | ||
| 39 | OmniJev 0.8B (tinnel123) | 26.8 | Official leaderboard | ||
| 40 | Gevva E2B multimodal | 21.9 | Official leaderboard | ||
| 41 | JEVision (divyanshx11, visual route) | 21.5 | Official leaderboard | ||
| 42 | Bonsai-2-27B v2 PQ2_0 + Q8_0 MMProj | 19.3 | Official leaderboard | ||
| 43 | Qevi-2B (MeerDevelopment) | 17.4 | Official leaderboard | ||
| 44 | GPT-6 Luna | 16.1 | OpenRouter reasoning.effort=low | Sep 2026 | Official leaderboard |
| 45 | GPT-5.6 Luna | 11.1 | Jul 2026 | Official leaderboard | |
| 46 | | 9.58 | Mar 2026 | Official leaderboard | |
| 47 | PlayJev 0.8B | 0.11 | Official leaderboard | ||
| 48 | | 0.00 | Sep 2026 | Official leaderboard | |
| 49 | OpenJev 4B NLI v2 (official image-premise path) | 0.00 | Official leaderboard | ||
| 50 | OpenJev 4B NLI v5 | 0.00 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | 16.1 | OpenRouter reasoning.effort=low | Sep 2026 | Official leaderboard |
| 2 | GPT-5.6 Luna | 11.1 | Jul 2026 | Official leaderboard | |
| 3 | | 9.58 | Mar 2026 | Official leaderboard | |
| 4 | | 0.00 | Sep 2026 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Core, Everyday photo and Public accuracy. GPT-6 Luna leads 2 of them, and GPT-5.6 Luna leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Core
4 models we track have a score here.
- 1 GPT-6 Luna 17.1
- 2 GPT-5.6 Luna 10.9
- 3
Gemini 3.1 Flash-Lite 9.06
- 4
Gemini 3.8 Flash 0.00
Everyday photo
4 models we track have a score here.
- 1 GPT-6 Luna 13.6
- 2 GPT-5.6 Luna 11.4
- 3
Gemini 3.1 Flash-Lite 10.9
- 4
Gemini 3.8 Flash 0.09
Public accuracy
4 models we track have a score here.
- 1 GPT-5.6 Luna ↑1 92.5%
- 2 GPT-6 Luna ↓1 89%
- 3
Gemini 3.8 Flash ↑1 88.6%
- 4
Gemini 3.1 Flash-Lite ↓1 85.1%
Sealed accuracy
4 models we track have a score here.
- 1 GPT-5.6 Luna ↑1 95.6%
- 2
Gemini 3.8 Flash ↑2 94.3%
- 3
Gemini 3.1 Flash-Lite 91.9%
- 4 GPT-6 Luna ↓3 86.6%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official ImageJevBench v0.1.5 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ImageJevBench v0.1.5 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.
Versions
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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (50 entries).
- Pass Models scored 4 models we track, plus 46 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6 Luna.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3.8 Flash (#24).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on benchmarkheaven.com: 4 rows for models we track and 46 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.