BVB
The official leaderboard hasn’t scored a model released after Claude Fable 5.2 (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 68.4.
Multimodal agents rebuild real-world videos as animated Blender scenes by writing code. The renders are compared with the source video under a shared cost limit.
It had 31 Hugging Face paper upvotes and 120 GitHub stars.
- Made by
- BVB authors (Tang et al.)
- Released
- September 2026
- Kind
- Video understanding
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Computer and information sciences, Arts
- Language
- English
- Interaction
- Agentic
- Environment
- Blender
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Vision, Image, video and 3D generation
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
In the authors’ words
Multimodal agents can create complex videos in software such as Blender by writing code instead of using diffusion models. Yet video understanding benchmarks still evaluate models mainly through question answering. If an agent truly understands a video, it can reconstruct it programmatically. We introduce BVB, Blender-VideoBench, a benchmark that tests this ability by asking agents to reconstruct real-world videos as animated Blender scenes. To ensure fair comparison, each agent programs the reconstruction through a lightweight harness, Mini-BVB, in an identical sandbox under a shared cost limit. The benchmark renders each reconstruction from its animated camera and evaluates it on two axes: (1) Dual VQA measures how many spatiotemporal facts the reconstruction preserves. (2) Latent Similarity measures how closely the reconstruction matches the source video perceptually. Our overall score, a square-root mean, favors balanced performance. We evaluate 51 configurations from 10 model families and analyze semantic retention, perceptual similarity, reasoning effort, and cost. The best model reaches 88.6 Latent Similarity but retains only 53.7% of the spatiotemporal facts from the source video. Additional reasoning improves perceptual similarity but does not close this gap. In a blind study with 15 raters and five configurations, Latent Similarity correlates strongly with human preference. These results show that programmatic reconstruction is a viable test of agentic video understanding, and that semantic retention remains the main challenge.
Claude Fable 5.2 leads with 76.4 Claude Fable 5.2 leads with 76.4
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. Every run is in the next chart. 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.
Claude Fable 5.2 leads with 76.4, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 76.4 Claude Fable 5.2
- 76.3 GPT-6 Astra
- 75.4 GPT-6.1 Sol
- 75.2 GPT-6.1 Terra
- 73.4 GPT-6 Sol
- 72.7
Gemini 4 Argon
- 72.4 Claude Opus 5.5
- 72.3 Claude Sonnet 5.5
- 71.8 GPT-5.6 Sol
- 71.6
Inkling 2 Small
- 70.9 Grok 4.6
- 70.3 GPT-6 Luna
- 70.1 Grok 4.7
- 70.0
DeepSeek V4.1 Flash 1017
- 69.5 Claude Opus 5
- 69.4
Qwen 3.8 Max
- 68.9 Glimpse
- 68.8 GPT-5.6 Terra
- 68.5 GPT-5.5
- 68.4 Claude Haiku 5.5
- 67.9 GLM-5.3-Flash
- 67.4
Muse Wonder
- 67.1
Muse Spark 1.3
- 66.8
DeepSeek V4.1 Flash
- 66.7 GPT-5.6 Luna
- 66.4 Grok 4.5
- 65.9
Gemini 3.8 Flash
- 65.3 Claude Sonnet 4.6
- 65.2 GPT-5.2
- 64.6 Claude Sonnet 5
- 64.6
Gemini 3.1 Pro
- 64.1 Claude Opus 4.6
- 63.6 Claude Opus 4.7
- 63.4
Muse Spark 1.2
- 62.5 Claude Opus 4.8
- 62.1
Gemini 3 Flash
- 60.5 GPT-5.4
- 60.2 GPT-5.4 Mini
- 59.6 Kimi K2.5
- 59.0 GLM-5V-Turbo
- 59.0
Inkling-Small
- 58.2
MiniMax-M3
- 56.9
Qwen3.5-122B-A10B
- 56.6 Grok 4.3
- 56.3
Qwen3.5 397B-A17B
- 55.9
Seed2.0 Mini
- 53.9
Qwen 3.6 Plus
- 52.1
Nemotron 3.5 Super VL
- 51.9
Seed2.0 Lite (0215)
- 50.7
Qwen3.5-27B
- 1 Claude Fable 5.2 xhigh 76.4
- 2 GPT-6 Astra xhigh 76.3
- 3 GPT-6.1 Sol xhigh 75.4
- 4 GPT-6.1 Terra xhigh 75.2
- 5 GPT-6 Sol xhigh 73.4
- 6
Gemini 4 Argon high 72.7
- 7 Claude Opus 5.5 xhigh 72.4
- 8 Claude Sonnet 5.5 xhigh 72.3
- 9 GPT-5.6 Sol xhigh 71.8
- 10
Inkling 2 Small max, Max · RC17 · effort 1, BVB Worm variant 71.6
- 11 Grok 4.6 xhigh 70.9
- 12 GPT-6 Luna xhigh 70.3
- 13 Grok 4.7 xhigh 70.1
- 14
DeepSeek V4.1 Flash 1017 max 70.0
- 15 Claude Opus 5 high 69.5
- 16
Qwen 3.8 Max high 69.4
- 17 Glimpse max 68.9
- 18 GPT-5.6 Terra high 68.8
- 19 GPT-5.5 high 68.5
- 20 Claude Haiku 5.5 xhigh 68.4
- 21 GLM-5.3-Flash xhigh 67.9
- 22
Muse Wonder xhigh 67.4
- 23
Muse Spark 1.3 xhigh 67.1
- 24
DeepSeek V4.1 Flash max 66.8
- 25 GPT-5.6 Luna high 66.7
- 26 Grok 4.5 high 66.4
- 27
Gemini 3.8 Flash high 65.9
- 28 Claude Sonnet 4.6 none 65.3
- 29 GPT-5.2 high 65.2
- 30 Claude Sonnet 5 none 64.6
- 31
Gemini 3.1 Pro high 64.6
- 32 Claude Opus 4.6 none 64.1
- 33 Claude Opus 4.7 none 63.6
- 34
Muse Spark 1.2 xhigh 63.4
- 35 Claude Opus 4.8 none 62.5
- 36
Gemini 3 Flash high 62.1
- 37 GPT-5.4 none 60.5
- 38 GPT-5.4 Mini none 60.2
- 39 Kimi K2.5 none 59.6
- 40 GLM-5V-Turbo none 59.0
- 41
Inkling-Small xhigh 59.0
- 42
MiniMax-M3 none 58.2
- 43
Qwen3.5-122B-A10B none 56.9
- 44 Grok 4.3 high 56.6
- 45
Qwen3.5 397B-A17B none 56.3
- 46
Seed2.0 Mini none 55.9
- 47
Qwen 3.6 Plus none 53.9
- 48
Nemotron 3.5 Super VL max 52.1
- 49
Seed2.0 Lite (0215) none 51.9
- 50
Qwen3.5-27B none 50.7
Source: Official BVB leaderboard
- 76.4 Claude Fable 5.2
- 76.3 GPT-6 Astra
- 75.4 GPT-6.1 Sol
- 75.2 GPT-6.1 Terra
- 73.4 GPT-6 Sol
- 72.7
Gemini 4 Argon
- 72.4 Claude Opus 5.5
- 72.3 Claude Sonnet 5.5
- 71.8 GPT-5.6 Sol
- 71.6
Inkling 2 Small
- 70.9 Grok 4.6
- 70.3 GPT-6 Luna
- 70.1 Grok 4.7
- 70.0
DeepSeek V4.1 Flash 1017
- 69.5 Claude Opus 5
- 69.4
Qwen 3.8 Max
- 68.8 GPT-5.6 Terra
- 68.5 GPT-5.5
- 68.4 Claude Haiku 5.5
- 67.9 GLM-5.3-Flash
- 67.4
Muse Wonder
- 67.1
Muse Spark 1.3
- 66.8
DeepSeek V4.1 Flash
- 66.7 GPT-5.6 Luna
- 66.4 Grok 4.5
- 65.9
Gemini 3.8 Flash
- 65.3 Claude Sonnet 4.6
- 65.2 GPT-5.2
- 64.6 Claude Sonnet 5
- 64.6
Gemini 3.1 Pro
- 64.1 Claude Opus 4.6
- 63.6 Claude Opus 4.7
- 63.4
Muse Spark 1.2
- 62.5 Claude Opus 4.8
- 62.1
Gemini 3 Flash
- 60.5 GPT-5.4
- 60.2 GPT-5.4 Mini
- 59.6 Kimi K2.5
- 59.0 GLM-5V-Turbo
- 59.0
Inkling-Small
- 58.2
MiniMax-M3
- 56.9
Qwen3.5-122B-A10B
- 56.6 Grok 4.3
- 56.3
Qwen3.5 397B-A17B
- 55.9
Seed2.0 Mini
- 53.9
Qwen 3.6 Plus
- 52.1
Nemotron 3.5 Super VL
- 51.9
Seed2.0 Lite (0215)
- 50.7
Qwen3.5-27B
- 1 Claude Fable 5.2 xhigh 76.4
- 2 GPT-6 Astra xhigh 76.3
- 3 GPT-6.1 Sol xhigh 75.4
- 4 GPT-6.1 Terra xhigh 75.2
- 5 GPT-6 Sol xhigh 73.4
- 6
Gemini 4 Argon high 72.7
- 7 Claude Opus 5.5 xhigh 72.4
- 8 Claude Sonnet 5.5 xhigh 72.3
- 9 GPT-5.6 Sol xhigh 71.8
- 10
Inkling 2 Small max, Max · RC17 · effort 1, BVB Worm variant 71.6
- 11 Grok 4.6 xhigh 70.9
- 12 GPT-6 Luna xhigh 70.3
- 13 Grok 4.7 xhigh 70.1
- 14
DeepSeek V4.1 Flash 1017 max 70.0
- 15 Claude Opus 5 high 69.5
- 16
Qwen 3.8 Max high 69.4
- 17 GPT-5.6 Terra high 68.8
- 18 GPT-5.5 high 68.5
- 19 Claude Haiku 5.5 xhigh 68.4
- 20 GLM-5.3-Flash xhigh 67.9
- 21
Muse Wonder xhigh 67.4
- 22
Muse Spark 1.3 xhigh 67.1
- 23
DeepSeek V4.1 Flash max 66.8
- 24 GPT-5.6 Luna high 66.7
- 25 Grok 4.5 high 66.4
- 26
Gemini 3.8 Flash high 65.9
- 27 Claude Sonnet 4.6 none 65.3
- 28 GPT-5.2 high 65.2
- 29 Claude Sonnet 5 none 64.6
- 30
Gemini 3.1 Pro high 64.6
- 31 Claude Opus 4.6 none 64.1
- 32 Claude Opus 4.7 none 63.6
- 33
Muse Spark 1.2 xhigh 63.4
- 34 Claude Opus 4.8 none 62.5
- 35
Gemini 3 Flash high 62.1
- 36 GPT-5.4 none 60.5
- 37 GPT-5.4 Mini none 60.2
- 38 Kimi K2.5 none 59.6
- 39 GLM-5V-Turbo none 59.0
- 40
Inkling-Small xhigh 59.0
- 41
MiniMax-M3 none 58.2
- 42
Qwen3.5-122B-A10B none 56.9
- 43 Grok 4.3 high 56.6
- 44
Qwen3.5 397B-A17B none 56.3
- 45
Seed2.0 Mini none 55.9
- 46
Qwen 3.6 Plus none 53.9
- 47
Nemotron 3.5 Super VL max 52.1
- 48
Seed2.0 Lite (0215) none 51.9
- 49
Qwen3.5-27B none 50.7
Source: Official BVB leaderboard
- 76.4 Claude Fable 5.2
- 76.3 GPT-6 Astra
- 75.4 GPT-6.1 Sol
- 75.2 GPT-6.1 Terra
- 73.4 GPT-6 Sol
- 72.7
Gemini 4 Argon
- 72.4 Claude Opus 5.5
- 72.3 Claude Sonnet 5.5
- 71.8 GPT-5.6 Sol
- 71.6
Inkling 2 Small
- 70.9 Grok 4.6
- 70.3 GPT-6 Luna
- 70.1 Grok 4.7
- 70.0
DeepSeek V4.1 Flash 1017
- 69.5 Claude Opus 5
- 69.4
Qwen 3.8 Max
- 68.8 GPT-5.6 Terra
- 68.5 GPT-5.5
- 68.4
Inkling 2 Mini
- 68.4 Claude Haiku 5.5
- 67.9 GLM-5.3-Flash
- 67.4
Muse Wonder
- 67.1
Muse Spark 1.3
- 66.8
DeepSeek V4.1 Flash
- 66.7 GPT-5.6 Luna
- 66.4 Grok 4.5
- 65.9
Gemini 3.8 Flash
- 65.3 Claude Sonnet 4.6
- 65.2 GPT-5.2
- 64.6 Claude Sonnet 5
- 64.6
Gemini 3.1 Pro
- 64.1 Claude Opus 4.6
- 63.6 Claude Opus 4.7
- 63.4
Muse Spark 1.2
- 62.5 Claude Opus 4.8
- 62.1
Gemini 3 Flash
- 60.5 GPT-5.4
- 60.2 GPT-5.4 Mini
- 59.6 Kimi K2.5
- 59.0 GLM-5V-Turbo
- 59.0
Inkling-Small
- 58.2
MiniMax-M3
- 56.9
Qwen3.5-122B-A10B
- 56.6 Grok 4.3
- 56.3
Qwen3.5 397B-A17B
- 55.9
Seed2.0 Mini
- 53.9
Qwen 3.6 Plus
- 52.1
Nemotron 3.5 Super VL
- 51.9
Seed2.0 Lite (0215)
- 50.7
Qwen3.5-27B
- 1 Claude Fable 5.2 xhigh 76.4
- 2 GPT-6 Astra xhigh 76.3
- 3 GPT-6.1 Sol xhigh 75.4
- 4 GPT-6.1 Terra xhigh 75.2
- 5 GPT-6 Sol xhigh 73.4
- 6
Gemini 4 Argon high 72.7
- 7 Claude Opus 5.5 xhigh 72.4
- 8 Claude Sonnet 5.5 xhigh 72.3
- 9 GPT-5.6 Sol xhigh 71.8
- 10
Inkling 2 Small max, Max · RC17 · effort 1, BVB Worm variant 71.6
- 11 Grok 4.6 xhigh 70.9
- 12 GPT-6 Luna xhigh 70.3
- 13 Grok 4.7 xhigh 70.1
- 14
DeepSeek V4.1 Flash 1017 max 70.0
- 15 Claude Opus 5 high 69.5
- 16
Qwen 3.8 Max high 69.4
- 17 GPT-5.6 Terra high 68.8
- 18 GPT-5.5 high 68.5
- 19
Inkling 2 Mini 68.4
- 20 Claude Haiku 5.5 xhigh 68.4
- 21 GLM-5.3-Flash xhigh 67.9
- 22
Muse Wonder xhigh 67.4
- 23
Muse Spark 1.3 xhigh 67.1
- 24
DeepSeek V4.1 Flash max 66.8
- 25 GPT-5.6 Luna high 66.7
- 26 Grok 4.5 high 66.4
- 27
Gemini 3.8 Flash high 65.9
- 28 Claude Sonnet 4.6 none 65.3
- 29 GPT-5.2 high 65.2
- 30 Claude Sonnet 5 none 64.6
- 31
Gemini 3.1 Pro high 64.6
- 32 Claude Opus 4.6 none 64.1
- 33 Claude Opus 4.7 none 63.6
- 34
Muse Spark 1.2 xhigh 63.4
- 35 Claude Opus 4.8 none 62.5
- 36
Gemini 3 Flash high 62.1
- 37 GPT-5.4 none 60.5
- 38 GPT-5.4 Mini none 60.2
- 39 Kimi K2.5 none 59.6
- 40 GLM-5V-Turbo none 59.0
- 41
Inkling-Small xhigh 59.0
- 42
MiniMax-M3 none 58.2
- 43
Qwen3.5-122B-A10B none 56.9
- 44 Grok 4.3 high 56.6
- 45
Qwen3.5 397B-A17B none 56.3
- 46
Seed2.0 Mini none 55.9
- 47
Qwen 3.6 Plus none 53.9
- 48
Nemotron 3.5 Super VL max 52.1
- 49
Seed2.0 Lite (0215) none 51.9
- 50
Qwen3.5-27B none 50.7
Sources: Official BVB leaderboard and labs’ model cards
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 76.4 | xhigh, mini-BVB | Nov 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 76.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 75.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Terra | 75.2 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 5 | GPT-6 Sol | 73.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 6 | | 72.7 | high, mini-BVB | Sep 2026 | Official leaderboard |
| 7 | Claude Opus 5.5 | 72.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 8 | Claude Sonnet 5.5 | 72.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 9 | GPT-5.6 Sol | 71.8 | xhigh, mini-BVB | Jul 2026 | Official leaderboard |
| 10 | | 71.6 | max, Max · RC17 · effort 1, BVB Worm variant | Nov 2026 | Official leaderboard |
| 11 | Grok 4.6 | 70.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 12 | GPT-6 Luna | 70.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 13 | Grok 4.7 | 70.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 14 | | 70.0 | max, mini-BVB | Oct 2026 | Official leaderboard |
| 15 | Claude Opus 5 | 69.5 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 16 | | 69.4 | high, mini-BVB | Aug 2026 | Official leaderboard |
| 17 | Glimpse closed weights | 68.9 | max, mini-BVB | Official leaderboard | |
| 18 | GPT-5.6 Terra | 68.8 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 19 | GPT-5.5 | 68.5 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 20 | Claude Haiku 5.5 | 68.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 21 | GLM-5.3-Flash | 67.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 22 | | 67.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 23 | | 67.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 24 | | 66.8 | max, mini-BVB | Sep 2026 | Official leaderboard |
| 25 | GPT-5.6 Luna | 66.7 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 26 | Grok 4.5 | 66.4 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 27 | | 65.9 | high, mini-BVB | Sep 2026 | Official leaderboard |
| 28 | Claude Sonnet 4.6 | 65.3 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 29 | GPT-5.2 | 65.2 | high, mini-BVB | Dec 2025 | Official leaderboard |
| 30 | Claude Sonnet 5 | 64.6 | none, mini-BVB | Jun 2026 | Official leaderboard |
| 31 | | 64.6 | high, mini-BVB | Feb 2026 | Official leaderboard |
| 32 | Claude Opus 4.6 | 64.1 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 33 | Claude Opus 4.7 | 63.6 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 34 | | 63.4 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 35 | Claude Opus 4.8 | 62.5 | none, mini-BVB | May 2026 | Official leaderboard |
| 36 | | 62.1 | high, mini-BVB | Dec 2025 | Official leaderboard |
| 37 | GPT-5.4 | 60.5 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 38 | GPT-5.4 Mini | 60.2 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 39 | Kimi K2.5 | 59.6 | none, mini-BVB | Jan 2026 | Official leaderboard |
| 40 | GLM-5V-Turbo | 59.0 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 41 | | 59.0 | xhigh | Jul 2026 | Official leaderboard |
| 42 | | 58.2 | none, mini-BVB | Jun 2026 | Official leaderboard |
| 43 | | 56.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 44 | Grok 4.3 | 56.6 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 45 | | 56.3 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 46 | | 55.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 47 | | 53.9 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 48 | | 52.1 | max, mini-BVB | Oct 2026 | Official leaderboard |
| 49 | | 51.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 50 | | 50.7 | none, mini-BVB | Feb 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 76.4 | xhigh, mini-BVB | Nov 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 76.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 75.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Terra | 75.2 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 5 | GPT-6 Sol | 73.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 6 | | 72.7 | high, mini-BVB | Sep 2026 | Official leaderboard |
| 7 | Claude Opus 5.5 | 72.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 8 | Claude Sonnet 5.5 | 72.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 9 | GPT-5.6 Sol | 71.8 | xhigh, mini-BVB | Jul 2026 | Official leaderboard |
| 10 | | 71.6 | max, Max · RC17 · effort 1, BVB Worm variant | Nov 2026 | Official leaderboard |
| 11 | Grok 4.6 | 70.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 12 | GPT-6 Luna | 70.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 13 | Grok 4.7 | 70.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 14 | | 70.0 | max, mini-BVB | Oct 2026 | Official leaderboard |
| 15 | Claude Opus 5 | 69.5 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 16 | | 69.4 | high, mini-BVB | Aug 2026 | Official leaderboard |
| 17 | GPT-5.6 Terra | 68.8 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 18 | GPT-5.5 | 68.5 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 19 | Claude Haiku 5.5 | 68.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 20 | GLM-5.3-Flash | 67.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 21 | | 67.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 22 | | 67.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 23 | | 66.8 | max, mini-BVB | Sep 2026 | Official leaderboard |
| 24 | GPT-5.6 Luna | 66.7 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 25 | Grok 4.5 | 66.4 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 26 | | 65.9 | high, mini-BVB | Sep 2026 | Official leaderboard |
| 27 | Claude Sonnet 4.6 | 65.3 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 28 | GPT-5.2 | 65.2 | high, mini-BVB | Dec 2025 | Official leaderboard |
| 29 | Claude Sonnet 5 | 64.6 | none, mini-BVB | Jun 2026 | Official leaderboard |
| 30 | | 64.6 | high, mini-BVB | Feb 2026 | Official leaderboard |
| 31 | Claude Opus 4.6 | 64.1 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 32 | Claude Opus 4.7 | 63.6 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 33 | | 63.4 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 34 | Claude Opus 4.8 | 62.5 | none, mini-BVB | May 2026 | Official leaderboard |
| 35 | | 62.1 | high, mini-BVB | Dec 2025 | Official leaderboard |
| 36 | GPT-5.4 | 60.5 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 37 | GPT-5.4 Mini | 60.2 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 38 | Kimi K2.5 | 59.6 | none, mini-BVB | Jan 2026 | Official leaderboard |
| 39 | GLM-5V-Turbo | 59.0 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 40 | | 59.0 | xhigh | Jul 2026 | Official leaderboard |
| 41 | | 58.2 | none, mini-BVB | Jun 2026 | Official leaderboard |
| 42 | | 56.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 43 | Grok 4.3 | 56.6 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 44 | | 56.3 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 45 | | 55.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 46 | | 53.9 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 47 | | 52.1 | max, mini-BVB | Oct 2026 | Official leaderboard |
| 48 | | 51.9 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 49 | | 50.7 | none, mini-BVB | Feb 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 76.4 | xhigh, mini-BVB | Nov 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 76.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 75.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Terra | 75.2 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 5 | GPT-6 Sol | 73.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 6 | 72.7 | high, mini-BVB | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 72.4 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 8 | Claude Sonnet 5.5 | 72.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 9 | GPT-5.6 Sol | 71.8 | xhigh, mini-BVB | Jul 2026 | Official leaderboard |
| 10 | 71.6 | max, Max · RC17 · effort 1, BVB Worm variant | Nov 2026 | Official leaderboard | |
| 11 | Grok 4.6 | 70.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 12 | GPT-6 Luna | 70.3 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 13 | Grok 4.7 | 70.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard |
| 14 | 70.0 | max, mini-BVB | Oct 2026 | Official leaderboard | |
| 15 | Claude Opus 5 | 69.5 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 16 | 69.4 | high, mini-BVB | Aug 2026 | Official leaderboard | |
| 17 | GPT-5.6 Terra | 68.8 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 18 | GPT-5.5 | 68.5 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 19 | 68.4 | Nov 2026 | Lab model card | ||
| 20 | Claude Haiku 5.5 | 68.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard |
| 21 | GLM-5.3-Flash | 67.9 | xhigh, mini-BVB | Aug 2026 | Official leaderboard |
| 22 | 67.4 | xhigh, mini-BVB | Oct 2026 | Official leaderboard | |
| 23 | 67.1 | xhigh, mini-BVB | Sep 2026 | Official leaderboard | |
| 24 | 66.8 | max, mini-BVB | Sep 2026 | Official leaderboard | |
| 25 | GPT-5.6 Luna | 66.7 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 26 | Grok 4.5 | 66.4 | high, mini-BVB | Jul 2026 | Official leaderboard |
| 27 | 65.9 | high, mini-BVB | Sep 2026 | Official leaderboard | |
| 28 | Claude Sonnet 4.6 | 65.3 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 29 | GPT-5.2 | 65.2 | high, mini-BVB | Dec 2025 | Official leaderboard |
| 30 | Claude Sonnet 5 | 64.6 | none, mini-BVB | Jun 2026 | Official leaderboard |
| 31 | 64.6 | high, mini-BVB | Feb 2026 | Official leaderboard | |
| 32 | Claude Opus 4.6 | 64.1 | none, mini-BVB | Feb 2026 | Official leaderboard |
| 33 | Claude Opus 4.7 | 63.6 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 34 | 63.4 | xhigh, mini-BVB | Aug 2026 | Official leaderboard | |
| 35 | Claude Opus 4.8 | 62.5 | none, mini-BVB | May 2026 | Official leaderboard |
| 36 | 62.1 | high, mini-BVB | Dec 2025 | Official leaderboard | |
| 37 | GPT-5.4 | 60.5 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 38 | GPT-5.4 Mini | 60.2 | none, mini-BVB | Mar 2026 | Official leaderboard |
| 39 | Kimi K2.5 | 59.6 | none, mini-BVB | Jan 2026 | Official leaderboard |
| 40 | GLM-5V-Turbo | 59.0 | none, mini-BVB | Apr 2026 | Official leaderboard |
| 41 | 59.0 | xhigh | Jul 2026 | Official leaderboard | |
| 42 | 58.2 | none, mini-BVB | Jun 2026 | Official leaderboard | |
| 43 | 56.9 | none, mini-BVB | Feb 2026 | Official leaderboard | |
| 44 | Grok 4.3 | 56.6 | high, mini-BVB | Apr 2026 | Official leaderboard |
| 45 | 56.3 | none, mini-BVB | Feb 2026 | Official leaderboard | |
| 46 | 55.9 | none, mini-BVB | Feb 2026 | Official leaderboard | |
| 47 | 53.9 | none, mini-BVB | Mar 2026 | Official leaderboard | |
| 48 | 52.1 | max, mini-BVB | Oct 2026 | Official leaderboard | |
| 49 | 51.9 | none, mini-BVB | Feb 2026 | Official leaderboard | |
| 50 | 50.7 | none, mini-BVB | Feb 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. Switch the scores above to rank them together.
Rankings by part
We read 12 parts from the benchmark’s own leaderboard in 2 groups: dimension and task type. Each ranks models on one part of the test. Claude Fable 5.2 leads 4 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Dual VQA
49 models we track have a score here.
- 1 Claude Fable 5.2 66.5
- 2 GPT-6 Astra 64.7
- 3 GPT-6.1 Terra ↑1 63.1
- 4 GPT-6.1 Sol ↓1 62.4
- 5 GPT-6 Sol 62.2
- 6 Claude Sonnet 5.5 ↑2 61.5
- 7 Claude Opus 5.5 61.3
- 8
Gemini 4 Argon ↓2 61.2
- 9
Inkling 2 Small ↑1 59.9
- 10 GPT-5.6 Sol ↓1 59.4
Latent similarity
49 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 89.7
- 2 GPT-6 Astra 88.9
- 3 GPT-6.1 Terra ↑1 88.2
- 4 Claude Fable 5.2 ↓3 87.1
- 5 GPT-6 Sol 85.6
- 6 GPT-5.6 Sol ↑3 85.4
- 7
Gemini 4 Argon ↓1 85.2
- 8 Claude Opus 5.5 ↓1 84.5
- 9 Grok 4.6 ↑2 84.2
- 10
Inkling 2 Small 84.2
Layout
48 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 88.4
- 2 GPT-6 Astra 87.6
- 3 GPT-6.1 Terra ↑1 86.9
- 4 Claude Fable 5.2 ↓3 85.9
- 5 GPT-6 Sol 84.2
- 6 GPT-5.6 Sol ↑3 84.0
- 7
Gemini 4 Argon ↓1 83.9
- 8 Claude Opus 5.5 ↓1 83.2
- 9 Grok 4.6 ↑2 82.9
- 10
Inkling 2 Small 82.7
Motion
48 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 91.0
- 2 GPT-6 Astra 90.2
- 3 GPT-6.1 Terra ↑1 89.5
- 4 Claude Fable 5.2 ↓3 88.3
- 5 GPT-6 Sol 87.0
- 6 GPT-5.6 Sol ↑3 86.7
- 7
Gemini 4 Argon ↓1 86.5
- 8
Inkling 2 Small ↑2 85.7
- 9 Claude Opus 5.5 ↓2 85.7
- 10 Grok 4.6 ↑1 85.5
Object counting
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 52.0
- 2 GPT-6 Astra 51.0
- 3 Claude Fable 5.2 ↓2 47.0
- 4 GPT-6 Sol ↑1 46.0
- 5 GPT-6.1 Terra ↓1 45.5
- 6 Claude Sonnet 5.5 ↑2 45.0
- 7
Gemini 4 Argon ↓1 43.5
- 8
Qwen 3.8 Max ↑8 42.5
- 9 Grok 4.7 ↑4 42.5
- 10 Claude Opus 5 ↑5 42.0
Object absolute distance
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 Claude Fable 5.2 56.6
- 2 GPT-6 Astra 52.6
- 3
DeepSeek V4.1 Flash ↑20 51.4
- 4 Claude Sonnet 5.5 ↑4 48.6
- 5 GPT-6 Sol 48.0
- 6 Grok 4.7 ↑7 47.4
- 7 GPT-6.1 Terra ↓3 46.8
- 8 Claude Opus 5 ↑7 46.2
- 9
Gemini 4 Argon ↓3 46.2
- 10
Muse Wonder ↑11 46.2
Object size estimation
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 GPT-6 Astra ↑1 76.5
- 2 Claude Fable 5.2 ↓1 76.1
- 3 GPT-6.1 Terra ↑1 74.1
- 4 Claude Opus 5.5 ↑3 73.7
- 5 GPT-6 Sol 73.1
- 6 GPT-6.1 Sol ↓3 72.9
- 7
DeepSeek V4.1 Flash 1017 ↑7 70.9
- 8
Gemini 4 Argon ↓2 70.5
- 9 Claude Sonnet 5.5 ↓1 70.3
- 10 Grok 4.7 ↑3 69.5
Room size estimation
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 GPT-6 Sol ↑4 59.2
- 2
DeepSeek V4.1 Flash 1017 ↑12 53.8
- 3 GPT-5.6 Sol ↑6 53.1
- 4 GPT-6.1 Terra 51.5
- 5 Grok 4.6 ↑6 46.9
- 6 Claude Opus 5.5 ↑1 46.9
- 7
Muse Wonder ↑14 46.9
- 8 GPT-5.2 ↑20 46.2
- 9 GPT-5.5 ↑9 46.2
- 10 GLM-5.3-Flash ↑10 46.2
Object relative distance
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 Claude Fable 5.2 59.0
- 2
Gemini 4 Argon ↑4 53.6
- 3 GPT-6.1 Terra ↑1 52.7
- 4 GPT-6.1 Sol ↓1 51.9
- 5 Claude Opus 5.5 ↑2 51.0
- 6 GPT-6 Astra ↓4 50.2
- 7 GPT-5.4 Mini ↑30 49.4
- 8 GPT-5.6 Sol ↑1 49.4
- 9 GPT-6 Sol ↓4 48.1
- 10 Claude Sonnet 5.5 ↓2 48.1
Object relative direction
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 GPT-6 Astra ↑1 77.5
- 2 Claude Fable 5.2 ↓1 77.3
- 3 Claude Sonnet 5.5 ↑5 76.5
- 4 GLM-5.3-Flash ↑16 76.3
- 5 GPT-5.6 Sol ↑4 75.5
- 6 GPT-6 Luna ↑6 74.8
- 7
Gemini 4 Argon ↓1 74.6
- 8 GPT-5.5 ↑10 74.3
- 9 Claude Opus 5.5 ↓2 74.3
- 10 Claude Sonnet 4.6 ↑17 74.1
Route planning
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 GPT-5.5 ↑17 81.8
- 2 GPT-5.6 Sol ↑7 81.8
- 3 GPT-6.1 Terra ↑1 81.8
- 4 Claude Fable 5.2 ↓3 81.8
- 5 Claude Sonnet 5.5 ↑3 80.3
- 6 Claude Opus 4.6 ↑25 78.8
- 7 Claude Opus 5 ↑8 78.8
- 8 Grok 4.6 ↑3 78.8
- 9 GPT-6 Luna ↑3 78.8
- 10
DeepSeek V4.1 Flash 1017 ↑4 78.8
Object appearance order
Dual VQA retention for this question type. 47 models we track have a score here.
- 1 Claude Fable 5.2 65.7
- 2
Qwen 3.8 Max ↑14 62.4
- 3 Claude Opus 4.8 ↑31 61.5
- 4 GLM-5.3-Flash ↑16 61.0
- 5 GPT-6.1 Terra ↓1 60.6
- 6 GPT-6 Astra ↓4 60.1
- 7
Muse Spark 1.3 ↑15 59.6
- 8 GPT-6 Luna ↑4 59.2
- 9
Gemini 4 Argon ↓3 59.2
- 10 GPT-5.2 ↑18 58.2
BVB score versus cost per scene
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Overall score | Cost per scene |
|---|---|---|---|
| Claude Fable 5.2 | xhigh, mini-BVB | 76.44 score | $2.61 |
| GPT-6 Astra | xhigh, mini-BVB | 76.33 score | $1.72 |
| GPT-6.1 Sol | xhigh, mini-BVB | 75.41 score | $0.5 |
| GPT-6.1 Terra | xhigh, mini-BVB | 75.16 score | $0.3 |
| GPT-6 Astra | high, mini-BVB | 73.95 score | $1.26 |
| GPT-6 Sol | xhigh, mini-BVB | 73.41 score | $0.4 |
| high, mini-BVB | 72.69 score | $0.31 | |
| Claude Opus 5.5 | xhigh, mini-BVB | 72.39 score | $1.95 |
| Claude Sonnet 5.5 | xhigh, mini-BVB | 72.27 score | $1.18 |
| GPT-5.6 Sol | xhigh, mini-BVB | 71.78 score | $0.78 |
| max, Max · RC17 · effort 1, BVB Worm variant | 71.56 score | $0.26 | |
| Grok 4.6 | xhigh, mini-BVB | 70.86 score | $1.68 |
| GPT-6 Luna | xhigh, mini-BVB | 70.32 score | $0.01 |
| Grok 4.7 | xhigh, mini-BVB | 70.07 score | $1.48 |
| max, mini-BVB | 70.02 score | $0.04 | |
| Claude Opus 5 | high, mini-BVB | 69.53 score | $2.16 |
| high, mini-BVB | 69.39 score | $0.6 | |
| GPT-5.6 Sol | high, mini-BVB | 69.21 score | $0.42 |
| Glimpse | max, mini-BVB | 68.86 score | $0.37 |
| GPT-5.6 Terra | high, mini-BVB | 68.76 score | $0.12 |
| GPT-5.5 | high, mini-BVB | 68.55 score | $0.96 |
| Claude Haiku 5.5 | xhigh, mini-BVB | 68.37 score | $0.03 |
| GPT-5.6 Terra | xhigh, mini-BVB | 68.37 score | $0.23 |
| Claude Opus 5.5 | high, mini-BVB | 68.15 score | $0.49 |
| GPT-5.6 Sol | none, mini-BVB | 68.08 score | $0.21 |
| GLM-5.3-Flash | xhigh, mini-BVB | 67.91 score | $0.02 |
| GPT-5.6 Sol | medium, mini-BVB | 67.9 score | $0.27 |
| xhigh, mini-BVB | 67.42 score | $1.33 | |
| xhigh, mini-BVB | 67.13 score | $0.23 | |
| max, mini-BVB | 66.82 score | $0.02 | |
| GPT-5.5 | medium, mini-BVB | 66.7 score | $0.56 |
| GPT-5.6 Luna | high, mini-BVB | 66.69 score | $0.08 |
| Grok 4.5 | high, mini-BVB | 66.42 score | $0.3 |
| GPT-5.6 Sol | low, mini-BVB | 66.28 score | $0.2 |
| GPT-5.6 Terra | medium, mini-BVB | 66.27 score | $0.15 |
| high, mini-BVB | 65.92 score | $0.63 | |
| GPT-5.5 | low, mini-BVB | 65.63 score | $0.32 |
| GPT-5.6 Luna | medium, mini-BVB | 65.59 score | $0.05 |
| Claude Sonnet 4.6 | none, mini-BVB | 65.29 score | $0.43 |
| GPT-5.2 | high, mini-BVB | 65.18 score | $0.58 |
| GPT-5.6 Terra | low, mini-BVB | 64.67 score | $0.15 |
| Claude Sonnet 5 | none, mini-BVB | 64.64 score | $0.64 |
| high, mini-BVB | 64.62 score | $0.67 | |
| Claude Sonnet 5 | high, mini-BVB | 64.16 score | $0.42 |
| Claude Opus 4.6 | none, mini-BVB | 64.09 score | $0.67 |
| Claude Sonnet 4.6 | high, mini-BVB | 64.05 score | $0.75 |
| Claude Opus 4.7 | none, mini-BVB | 63.57 score | $0.37 |
| xhigh, mini-BVB | 63.4 score | $0.24 | |
| GPT-5.6 Luna | low, mini-BVB | 63.24 score | $0.03 |
| Claude Opus 4.8 | none, mini-BVB | 62.55 score | $0.32 |
| Claude Opus 4.8 | high, mini-BVB | 62.21 score | $0.46 |
| high, mini-BVB | 62.14 score | $0.08 | |
| Claude Opus 4.7 | high, mini-BVB | 62.08 score | $0.35 |
| GPT-5.2 | none, mini-BVB | 61.87 score | $0.12 |
| GPT-5.4 | none, mini-BVB | 60.53 score | $0.2 |
| GPT-5.5 | none, mini-BVB | 60.34 score | $0.16 |
| GPT-5.4 Mini | none, mini-BVB | 60.16 score | $0.03 |
| Kimi K2.5 | none, mini-BVB | 59.64 score | $0.15 |
| GLM-5V-Turbo | none, mini-BVB | 59 score | $0.28 |
| none, mini-BVB | 58.18 score | $0.06 | |
| none, mini-BVB | 56.85 score | $0.23 | |
| Grok 4.3 | high, mini-BVB | 56.58 score | $0.1 |
| none, mini-BVB | 56.32 score | $0.18 | |
| none, mini-BVB | 55.87 score | $0.03 | |
| none, mini-BVB | 53.94 score | $0.17 | |
| Grok 4.3 | none, mini-BVB | 52.37 score | $0.05 |
| max, mini-BVB | 52.11 score | $0.12 | |
| none, mini-BVB | 51.9 score | $0.04 | |
| none, mini-BVB | 50.74 score | $0.07 |
BVB score versus cost per scene
The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Overall score | Cost per scene |
|---|---|---|---|
| Claude Fable 5.2 | xhigh, mini-BVB | 76.44 score | $2.61 |
| GPT-6 Astra | xhigh, mini-BVB | 76.33 score | $1.72 |
| GPT-6.1 Sol | xhigh, mini-BVB | 75.41 score | $0.5 |
| GPT-6.1 Terra | xhigh, mini-BVB | 75.16 score | $0.3 |
| GPT-6 Astra | high, mini-BVB | 73.95 score | $1.26 |
| GPT-6 Sol | xhigh, mini-BVB | 73.41 score | $0.4 |
| high, mini-BVB | 72.69 score | $0.31 | |
| Claude Opus 5.5 | xhigh, mini-BVB | 72.39 score | $1.95 |
| Claude Sonnet 5.5 | xhigh, mini-BVB | 72.27 score | $1.18 |
| GPT-5.6 Sol | xhigh, mini-BVB | 71.78 score | $0.78 |
| max, Max · RC17 · effort 1, BVB Worm variant | 71.56 score | $0.26 | |
| Grok 4.6 | xhigh, mini-BVB | 70.86 score | $1.68 |
| GPT-6 Luna | xhigh, mini-BVB | 70.32 score | $0.01 |
| Grok 4.7 | xhigh, mini-BVB | 70.07 score | $1.48 |
| max, mini-BVB | 70.02 score | $0.04 | |
| Claude Opus 5 | high, mini-BVB | 69.53 score | $2.16 |
| high, mini-BVB | 69.39 score | $0.6 | |
| GPT-5.6 Sol | high, mini-BVB | 69.21 score | $0.42 |
| GPT-5.6 Terra | high, mini-BVB | 68.76 score | $0.12 |
| GPT-5.5 | high, mini-BVB | 68.55 score | $0.96 |
| Claude Haiku 5.5 | xhigh, mini-BVB | 68.37 score | $0.03 |
| GPT-5.6 Terra | xhigh, mini-BVB | 68.37 score | $0.23 |
| Claude Opus 5.5 | high, mini-BVB | 68.15 score | $0.49 |
| GPT-5.6 Sol | none, mini-BVB | 68.08 score | $0.21 |
| GLM-5.3-Flash | xhigh, mini-BVB | 67.91 score | $0.02 |
| GPT-5.6 Sol | medium, mini-BVB | 67.9 score | $0.27 |
| xhigh, mini-BVB | 67.42 score | $1.33 | |
| xhigh, mini-BVB | 67.13 score | $0.23 | |
| max, mini-BVB | 66.82 score | $0.02 | |
| GPT-5.5 | medium, mini-BVB | 66.7 score | $0.56 |
| GPT-5.6 Luna | high, mini-BVB | 66.69 score | $0.08 |
| Grok 4.5 | high, mini-BVB | 66.42 score | $0.3 |
| GPT-5.6 Sol | low, mini-BVB | 66.28 score | $0.2 |
| GPT-5.6 Terra | medium, mini-BVB | 66.27 score | $0.15 |
| high, mini-BVB | 65.92 score | $0.63 | |
| GPT-5.5 | low, mini-BVB | 65.63 score | $0.32 |
| GPT-5.6 Luna | medium, mini-BVB | 65.59 score | $0.05 |
| Claude Sonnet 4.6 | none, mini-BVB | 65.29 score | $0.43 |
| GPT-5.2 | high, mini-BVB | 65.18 score | $0.58 |
| GPT-5.6 Terra | low, mini-BVB | 64.67 score | $0.15 |
| Claude Sonnet 5 | none, mini-BVB | 64.64 score | $0.64 |
| high, mini-BVB | 64.62 score | $0.67 | |
| Claude Sonnet 5 | high, mini-BVB | 64.16 score | $0.42 |
| Claude Opus 4.6 | none, mini-BVB | 64.09 score | $0.67 |
| Claude Sonnet 4.6 | high, mini-BVB | 64.05 score | $0.75 |
| Claude Opus 4.7 | none, mini-BVB | 63.57 score | $0.37 |
| xhigh, mini-BVB | 63.4 score | $0.24 | |
| GPT-5.6 Luna | low, mini-BVB | 63.24 score | $0.03 |
| Claude Opus 4.8 | none, mini-BVB | 62.55 score | $0.32 |
| Claude Opus 4.8 | high, mini-BVB | 62.21 score | $0.46 |
| high, mini-BVB | 62.14 score | $0.08 | |
| Claude Opus 4.7 | high, mini-BVB | 62.08 score | $0.35 |
| GPT-5.2 | none, mini-BVB | 61.87 score | $0.12 |
| GPT-5.4 | none, mini-BVB | 60.53 score | $0.2 |
| GPT-5.5 | none, mini-BVB | 60.34 score | $0.16 |
| GPT-5.4 Mini | none, mini-BVB | 60.16 score | $0.03 |
| Kimi K2.5 | none, mini-BVB | 59.64 score | $0.15 |
| GLM-5V-Turbo | none, mini-BVB | 59 score | $0.28 |
| none, mini-BVB | 58.18 score | $0.06 | |
| none, mini-BVB | 56.85 score | $0.23 | |
| Grok 4.3 | high, mini-BVB | 56.58 score | $0.1 |
| none, mini-BVB | 56.32 score | $0.18 | |
| none, mini-BVB | 55.87 score | $0.03 | |
| none, mini-BVB | 53.94 score | $0.17 | |
| Grok 4.3 | none, mini-BVB | 52.37 score | $0.05 |
| max, mini-BVB | 52.11 score | $0.12 | |
| none, mini-BVB | 51.9 score | $0.04 | |
| none, mini-BVB | 50.74 score | $0.07 |
The best score, 76.4, costs $2.61 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Terra at xhigh comes within 1.3 of the best for $0.30 a task, 9 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official BVB leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | xhigh | mini-BVB | 76.4 | $2.61 | |
| GPT-6 Astra | xhigh | mini-BVB | 76.3 | $1.72 | |
| GPT-6.1 Sol | xhigh | mini-BVB | 75.4 | $0.50 | |
| GPT-6.1 Terra | xhigh | mini-BVB | 75.2 | $0.30 | |
| GPT-6 Astra | high | mini-BVB | 74.0 | $1.26 | |
| GPT-6 Sol | xhigh | mini-BVB | 73.4 | $0.40 | |
| high | mini-BVB | 72.7 | $0.31 | ||
| Claude Opus 5.5 | xhigh | mini-BVB | 72.4 | $1.95 | |
| Claude Sonnet 5.5 | xhigh | mini-BVB | 72.3 | $1.18 | |
| GPT-5.6 Sol | xhigh | mini-BVB | 71.8 | $0.78 | |
| max, Max · RC17 · effort 1, BVB Worm variant | 71.6 | $0.26 | |||
| Grok 4.6 | xhigh | mini-BVB | 70.9 | $1.68 | |
| GPT-6 Luna | xhigh | mini-BVB | 70.3 | $0.01 | |
| Grok 4.7 | xhigh | mini-BVB | 70.1 | $1.48 | |
| max | mini-BVB | 70.0 | $0.04 | ||
| Claude Opus 5 | high | mini-BVB | 69.5 | $2.16 | |
| high | mini-BVB | 69.4 | $0.60 | ||
| GPT-5.6 Sol | high | mini-BVB | 69.2 | $0.42 | |
| GPT-5.6 Terra | high | mini-BVB | 68.8 | $0.12 | |
| GPT-5.5 | high | mini-BVB | 68.5 | $0.96 | |
| GPT-5.6 Terra | xhigh | mini-BVB | 68.4 | $0.23 | |
| Claude Haiku 5.5 | xhigh | mini-BVB | 68.4 | $0.03 | |
| Claude Opus 5.5 | high | mini-BVB | 68.2 | $0.49 | |
| GPT-5.6 Sol | none | mini-BVB | 68.1 | $0.21 | |
| GLM-5.3-Flash | xhigh | mini-BVB | 67.9 | $0.02 | |
| GPT-5.6 Sol | medium | mini-BVB | 67.9 | $0.27 | |
| xhigh | mini-BVB | 67.4 | $1.33 | ||
| xhigh | mini-BVB | 67.1 | $0.23 | ||
| max | mini-BVB | 66.8 | $0.02 | ||
| GPT-5.5 | medium | mini-BVB | 66.7 | $0.56 | |
| GPT-5.6 Luna | high | mini-BVB | 66.7 | $0.08 | |
| Grok 4.5 | high | mini-BVB | 66.4 | $0.30 | |
| GPT-5.6 Sol | low | mini-BVB | 66.3 | $0.20 | |
| GPT-5.6 Terra | medium | mini-BVB | 66.3 | $0.15 | |
| high | mini-BVB | 65.9 | $0.63 | ||
| GPT-5.5 | low | mini-BVB | 65.6 | $0.32 | |
| GPT-5.6 Luna | medium | mini-BVB | 65.6 | $0.05 | |
| Claude Sonnet 4.6 | none | mini-BVB | 65.3 | $0.43 | |
| GPT-5.2 | high | mini-BVB | 65.2 | $0.58 | |
| GPT-5.6 Terra | low | mini-BVB | 64.7 | $0.15 | |
| Claude Sonnet 5 | none | mini-BVB | 64.6 | $0.64 | |
| high | mini-BVB | 64.6 | $0.67 | ||
| Claude Sonnet 5 | high | mini-BVB | 64.2 | $0.42 | |
| Claude Opus 4.6 | none | mini-BVB | 64.1 | $0.67 | |
| Claude Sonnet 4.6 | high | mini-BVB | 64.0 | $0.75 | |
| Claude Opus 4.7 | none | mini-BVB | 63.6 | $0.37 | |
| xhigh | mini-BVB | 63.4 | $0.23 | ||
| GPT-5.6 Luna | low | mini-BVB | 63.2 | $0.03 | |
| Claude Opus 4.8 | none | mini-BVB | 62.5 | $0.32 | |
| Claude Opus 4.8 | high | mini-BVB | 62.2 | $0.46 | |
| high | mini-BVB | 62.1 | $0.08 | ||
| Claude Opus 4.7 | high | mini-BVB | 62.1 | $0.35 | |
| GPT-5.2 | none | mini-BVB | 61.9 | $0.12 | |
| GPT-5.4 | none | mini-BVB | 60.5 | $0.20 | |
| GPT-5.5 | none | mini-BVB | 60.3 | $0.16 | |
| GPT-5.4 Mini | none | mini-BVB | 60.2 | $0.03 | |
| Kimi K2.5 | none | mini-BVB | 59.6 | $0.15 | |
| GLM-5V-Turbo | none | mini-BVB | 59.0 | $0.28 | |
| xhigh | 59.0 | ||||
| none | mini-BVB | 58.2 | $0.06 | ||
| none | mini-BVB | 56.9 | $0.23 | ||
| Grok 4.3 | high | mini-BVB | 56.6 | $0.10 | |
| none | mini-BVB | 56.3 | $0.18 | ||
| none | mini-BVB | 55.9 | $0.03 | ||
| none | mini-BVB | 53.9 | $0.17 | ||
| Grok 4.3 | none | mini-BVB | 52.4 | $0.05 | |
| max | mini-BVB | 52.1 | $0.12 | ||
| none | mini-BVB | 51.9 | $0.04 | ||
| none | mini-BVB | 50.7 | $0.07 |
The best score, 76.4, costs $2.61 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Terra at xhigh comes within 1.3 of the best for $0.30 a task, 9 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official BVB leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | xhigh | mini-BVB | 76.4 | $2.61 | |
| GPT-6 Astra | xhigh | mini-BVB | 76.3 | $1.72 | |
| GPT-6.1 Sol | xhigh | mini-BVB | 75.4 | $0.50 | |
| GPT-6.1 Terra | xhigh | mini-BVB | 75.2 | $0.30 | |
| GPT-6 Astra | high | mini-BVB | 74.0 | $1.26 | |
| GPT-6 Sol | xhigh | mini-BVB | 73.4 | $0.40 | |
| high | mini-BVB | 72.7 | $0.31 | ||
| Claude Opus 5.5 | xhigh | mini-BVB | 72.4 | $1.95 | |
| Claude Sonnet 5.5 | xhigh | mini-BVB | 72.3 | $1.18 | |
| GPT-5.6 Sol | xhigh | mini-BVB | 71.8 | $0.78 | |
| max, Max · RC17 · effort 1, BVB Worm variant | 71.6 | $0.26 | |||
| Grok 4.6 | xhigh | mini-BVB | 70.9 | $1.68 | |
| GPT-6 Luna | xhigh | mini-BVB | 70.3 | $0.01 | |
| Grok 4.7 | xhigh | mini-BVB | 70.1 | $1.48 | |
| max | mini-BVB | 70.0 | $0.04 | ||
| Claude Opus 5 | high | mini-BVB | 69.5 | $2.16 | |
| high | mini-BVB | 69.4 | $0.60 | ||
| GPT-5.6 Sol | high | mini-BVB | 69.2 | $0.42 | |
| GPT-5.6 Terra | high | mini-BVB | 68.8 | $0.12 | |
| GPT-5.5 | high | mini-BVB | 68.5 | $0.96 | |
| GPT-5.6 Terra | xhigh | mini-BVB | 68.4 | $0.23 | |
| Claude Haiku 5.5 | xhigh | mini-BVB | 68.4 | $0.03 | |
| Claude Opus 5.5 | high | mini-BVB | 68.2 | $0.49 | |
| GPT-5.6 Sol | none | mini-BVB | 68.1 | $0.21 | |
| GLM-5.3-Flash | xhigh | mini-BVB | 67.9 | $0.02 | |
| GPT-5.6 Sol | medium | mini-BVB | 67.9 | $0.27 | |
| xhigh | mini-BVB | 67.4 | $1.33 | ||
| xhigh | mini-BVB | 67.1 | $0.23 | ||
| max | mini-BVB | 66.8 | $0.02 | ||
| GPT-5.5 | medium | mini-BVB | 66.7 | $0.56 | |
| GPT-5.6 Luna | high | mini-BVB | 66.7 | $0.08 | |
| Grok 4.5 | high | mini-BVB | 66.4 | $0.30 | |
| GPT-5.6 Sol | low | mini-BVB | 66.3 | $0.20 | |
| GPT-5.6 Terra | medium | mini-BVB | 66.3 | $0.15 | |
| high | mini-BVB | 65.9 | $0.63 | ||
| GPT-5.5 | low | mini-BVB | 65.6 | $0.32 | |
| GPT-5.6 Luna | medium | mini-BVB | 65.6 | $0.05 | |
| Claude Sonnet 4.6 | none | mini-BVB | 65.3 | $0.43 | |
| GPT-5.2 | high | mini-BVB | 65.2 | $0.58 | |
| GPT-5.6 Terra | low | mini-BVB | 64.7 | $0.15 | |
| Claude Sonnet 5 | none | mini-BVB | 64.6 | $0.64 | |
| high | mini-BVB | 64.6 | $0.67 | ||
| Claude Sonnet 5 | high | mini-BVB | 64.2 | $0.42 | |
| Claude Opus 4.6 | none | mini-BVB | 64.1 | $0.67 | |
| Claude Sonnet 4.6 | high | mini-BVB | 64.0 | $0.75 | |
| Claude Opus 4.7 | none | mini-BVB | 63.6 | $0.37 | |
| xhigh | mini-BVB | 63.4 | $0.23 | ||
| GPT-5.6 Luna | low | mini-BVB | 63.2 | $0.03 | |
| Claude Opus 4.8 | none | mini-BVB | 62.5 | $0.32 | |
| Claude Opus 4.8 | high | mini-BVB | 62.2 | $0.46 | |
| high | mini-BVB | 62.1 | $0.08 | ||
| Claude Opus 4.7 | high | mini-BVB | 62.1 | $0.35 | |
| GPT-5.2 | none | mini-BVB | 61.9 | $0.12 | |
| GPT-5.4 | none | mini-BVB | 60.5 | $0.20 | |
| GPT-5.5 | none | mini-BVB | 60.3 | $0.16 | |
| GPT-5.4 Mini | none | mini-BVB | 60.2 | $0.03 | |
| Kimi K2.5 | none | mini-BVB | 59.6 | $0.15 | |
| GLM-5V-Turbo | none | mini-BVB | 59.0 | $0.28 | |
| xhigh | 59.0 | ||||
| none | mini-BVB | 58.2 | $0.06 | ||
| none | mini-BVB | 56.9 | $0.23 | ||
| Grok 4.3 | high | mini-BVB | 56.6 | $0.10 | |
| none | mini-BVB | 56.3 | $0.18 | ||
| none | mini-BVB | 55.9 | $0.03 | ||
| none | mini-BVB | 53.9 | $0.17 | ||
| Grok 4.3 | none | mini-BVB | 52.4 | $0.05 | |
| max | mini-BVB | 52.1 | $0.12 | ||
| none | mini-BVB | 51.9 | $0.04 | ||
| none | mini-BVB | 50.7 | $0.07 |
3 models have held number one on the official leaderboard since its release in September 2026 3 models have held number one with claims included since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official BVB leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official BVB leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 20, 2026 | 68.4 | BVB |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 20, 2026 | | 68.4 | BVB | Capabilities |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (50 entries), launch posts (1 score) and system cards (1 score).
- Pass Models scored 50 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 7 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on yoloytang.me: 69 rows for models we track and 1 other entry 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.