Benchmark Almanac

Spatial Intelligence Index v2

Claude Opus 5.5 88.7 leads since November 2026
Not in model cards
Version 2

Models analyze geospatial data, follow guided workflows, and answer knowledge questions. Axis Spatial also grades image interpretation in its vision ranking.

Axis Spatial retains the original group weights. It accepts partial coverage and shows each model at its best ranked reasoning level.

Made by
Axis Spatial
Released
November 2026
Kind
Composite indices
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
Interaction
Agentic
Environment
APIs and tools
Items from
Another benchmark
Run by
Anyone
In views
Agents, Vision
Strongest model tested
Claude Opus 5.5 #5 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
40
Entries on its own leaderboard, 39 models we track

Claude Opus 5.5 leads with 88.7 Claude Opus 5.5 leads with 88.7

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.

  1. 1 Claude Opus 5.5 Text only, xhigh 88.7
  2. 2 GPT-6.1 Sol Text only, medium 86.4
  3. 3 GPT-6 Sol Text only, high 84.9
  4. 4 Claude Opus 5 Text only, high 84.7
  5. 5 Claude Sonnet 5.5 Text only, xhigh 84.4
  6. 6 Claude Opus 4.8 Text only, high 82.5
  7. 7 Claude Haiku 5.5 Text only, xhigh 82.0
  8. 8 Kimi K3 Text only, Reasoning 81.7
  9. 9 GPT-5.6 Sol Text only, high 81.6
  10. 10 Claude Sonnet 5 Text only, high 80.9
  11. 11 Claude Opus 4.7 Text only, high 80.8
  12. 12 GPT-5.6 Luna Text only, xhigh 80.0
  13. 13 GPT-6 Luna Text only, xhigh 80.0
  14. 14 DeepSeek-V4-Pro Text only, max 79.7
  15. 15 Gemini 3.8 Flash Text only, low 79.6
  16. 16 DeepSeek-V4-Flash Text only, high 78.7
  17. 17 GLM-5.2 Text only, high 78.6
  18. 18 GLM-5.3 Text only, max 78.4
  19. 19 GPT-5.6 Terra Text only, high 77.5
  20. 20 Qwen 3.8 27B Text only, xhigh 75.8
  21. 21 Nemotron 3 Ultra Text only, high 73.7
  22. 22 GLM-5.3-Flash Text only, low 72.1
  23. 23 Muse Glimmer Text only, high 68.4
  24. 24 Nemotron 3.5 Super 120B Text only, Reasoning 66.3
  25. 25 Claude Haiku 4.5 Text only, Reasoning 65.8
  26. 26 Step 5 Preview Text only, Reasoning 64.6
  27. 27 Gemma 4 26B A4B Text only, Reasoning 64.4
  28. 28 Gemini 3.1 Flash-Lite Text only, high 63.2
  29. 29 Qwen 3.6 35B-A3B Text only, Reasoning 62.3
  30. 30 MiniMax-M3.1-Flash Text only, max 61.3
  31. 31 Nemotron 3.5 Super VL Text only, Reasoning 59.0
  32. 32 gpt-oss-120b Text only, high 51.9
  33. 33 Laguna XS 2.1 Text only, Reasoning 50.3
  34. 34 glm-4.7-flash Text only, Reasoning 49.6
  35. 35 Mistral Large 3 Text only, Non-reasoning 44.5
  36. 36 Nemotron 3 Nano Omni 30B-A3B Text only, Reasoning 31.9
  37. 37 Nemotron 3.5 Lightning 30B-A3B Text only, Reasoning 27.4
  38. 38 gpt-oss-20b Text only, high 22.1
  39. 39 Llama 3.3 70B Text only, Non-reasoning 19.9
  40. 40 Nemotron 3.5 Bolt E4B Text only, Reasoning 16.5

Source: Official Spatial Intelligence Index v2 leaderboard

  1. 1 Claude Opus 5.5 Text only, xhigh 88.7
  2. 2 GPT-6.1 Sol Text only, medium 86.4
  3. 3 GPT-6 Sol Text only, high 84.9
  4. 4 Claude Opus 5 Text only, high 84.7
  5. 5 Claude Sonnet 5.5 Text only, xhigh 84.4
  6. 6 Claude Opus 4.8 Text only, high 82.5
  7. 7 Claude Haiku 5.5 Text only, xhigh 82.0
  8. 8 Kimi K3 Text only, Reasoning 81.7
  9. 9 GPT-5.6 Sol Text only, high 81.6
  10. 10 Claude Sonnet 5 Text only, high 80.9
  11. 11 Claude Opus 4.7 Text only, high 80.8
  12. 12 GPT-5.6 Luna Text only, xhigh 80.0
  13. 13 GPT-6 Luna Text only, xhigh 80.0
  14. 14 DeepSeek-V4-Pro Text only, max 79.7
  15. 15 Gemini 3.8 Flash Text only, low 79.6
  16. 16 DeepSeek-V4-Flash Text only, high 78.7
  17. 17 GLM-5.2 Text only, high 78.6
  18. 18 GLM-5.3 Text only, max 78.4
  19. 19 GPT-5.6 Terra Text only, high 77.5
  20. 20 Qwen 3.8 27B Text only, xhigh 75.8
  21. 21 Nemotron 3 Ultra Text only, high 73.7
  22. 22 GLM-5.3-Flash Text only, low 72.1
  23. 23 Muse Glimmer Text only, high 68.4
  24. 24 Claude Haiku 4.5 Text only, Reasoning 65.8
  25. 25 Step 5 Preview Text only, Reasoning 64.6
  26. 26 Gemma 4 26B A4B Text only, Reasoning 64.4
  27. 27 Gemini 3.1 Flash-Lite Text only, high 63.2
  28. 28 Qwen 3.6 35B-A3B Text only, Reasoning 62.3
  29. 29 MiniMax-M3.1-Flash Text only, max 61.3
  30. 30 Nemotron 3.5 Super VL Text only, Reasoning 59.0
  31. 31 gpt-oss-120b Text only, high 51.9
  32. 32 Laguna XS 2.1 Text only, Reasoning 50.3
  33. 33 glm-4.7-flash Text only, Reasoning 49.6
  34. 34 Mistral Large 3 Text only, Non-reasoning 44.5
  35. 35 Nemotron 3 Nano Omni 30B-A3B Text only, Reasoning 31.9
  36. 36 Nemotron 3.5 Lightning 30B-A3B Text only, Reasoning 27.4
  37. 37 gpt-oss-20b Text only, high 22.1
  38. 38 Llama 3.3 70B Text only, Non-reasoning 19.9
  39. 39 Nemotron 3.5 Bolt E4B Text only, Reasoning 16.5

Source: Official Spatial Intelligence Index v2 leaderboard

#EntryScoreSettingDateLinkSource
1 Claude Opus 5.5 88.7 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
2 GPT-6.1 Sol 86.4 Text only, medium Sep 2026 axisspatial.com Official leaderboard
3 GPT-6 Sol 84.9 Text only, high Sep 2026 axisspatial.com Official leaderboard
4 Claude Opus 5 84.7 Text only, high Jul 2026 axisspatial.com Official leaderboard
5 Claude Sonnet 5.5 84.4 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
6 Claude Opus 4.8 82.5 Text only, high May 2026 axisspatial.com Official leaderboard
7 Claude Haiku 5.5 82.0 Text only, xhigh Oct 2026 axisspatial.com Official leaderboard
8 Kimi K3 81.7 Text only, Reasoning Jul 2026 axisspatial.com Official leaderboard
9 GPT-5.6 Sol 81.6 Text only, high Jul 2026 axisspatial.com Official leaderboard
10 Claude Sonnet 5 80.9 Text only, high Jun 2026 axisspatial.com Official leaderboard
11 Claude Opus 4.7 80.8 Text only, high Apr 2026 axisspatial.com Official leaderboard
12 GPT-5.6 Luna 80.0 Text only, xhigh Jul 2026 axisspatial.com Official leaderboard
13 GPT-6 Luna 80.0 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
14 DeepSeek-V4-Pro 79.7 Text only, max Apr 2026 axisspatial.com Official leaderboard
15 Gemini 3.8 Flash 79.6 Text only, low Sep 2026 axisspatial.com Official leaderboard
16 DeepSeek-V4-Flash 78.7 Text only, high Apr 2026 axisspatial.com Official leaderboard
17 GLM-5.2 78.6 Text only, high Jun 2026 axisspatial.com Official leaderboard
18 GLM-5.3 78.4 Text only, max Aug 2026 axisspatial.com Official leaderboard
19 GPT-5.6 Terra 77.5 Text only, high Jul 2026 axisspatial.com Official leaderboard
20 Qwen 3.8 27B 75.8 Text only, xhigh Aug 2026 axisspatial.com Official leaderboard
21 Nemotron 3 Ultra 73.7 Text only, high Jun 2026 axisspatial.com Official leaderboard
22 GLM-5.3-Flash 72.1 Text only, low Aug 2026 axisspatial.com Official leaderboard
23 Muse Glimmer 68.4 Text only, high Aug 2026 axisspatial.com Official leaderboard
24 Nemotron 3.5 Super 120B open weights 66.3 Text only, Reasoning axisspatial.com Official leaderboard
25 Claude Haiku 4.5 65.8 Text only, Reasoning Oct 2025 axisspatial.com Official leaderboard
26 Step 5 Preview 64.6 Text only, Reasoning Sep 2026 axisspatial.com Official leaderboard
27 Gemma 4 26B A4B 64.4 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
28 Gemini 3.1 Flash-Lite 63.2 Text only, high Mar 2026 axisspatial.com Official leaderboard
29 Qwen 3.6 35B-A3B 62.3 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
30 MiniMax-M3.1-Flash 61.3 Text only, max Oct 2026 axisspatial.com Official leaderboard
31 Nemotron 3.5 Super VL 59.0 Text only, Reasoning Oct 2026 axisspatial.com Official leaderboard
32 gpt-oss-120b 51.9 Text only, high Aug 2025 axisspatial.com Official leaderboard
33 Laguna XS 2.1 50.3 Text only, Reasoning Jul 2026 axisspatial.com Official leaderboard
34 glm-4.7-flash 49.6 Text only, Reasoning Jan 2026 axisspatial.com Official leaderboard
35 Mistral Large 3 44.5 Text only, Non-reasoning Dec 2025 axisspatial.com Official leaderboard
36 Nemotron 3 Nano Omni 30B-A3B 31.9 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
37 Nemotron 3.5 Lightning 30B-A3B 27.4 Text only, Reasoning Aug 2026 axisspatial.com Official leaderboard
38 gpt-oss-20b 22.1 Text only, high Aug 2025 axisspatial.com Official leaderboard
39 Llama 3.3 70B 19.9 Text only, Non-reasoning Dec 2024 axisspatial.com Official leaderboard
40 Nemotron 3.5 Bolt E4B 16.5 Text only, Reasoning Oct 2026 axisspatial.com Official leaderboard
#ModelScoreSettingDateLinkSource
1 Claude Opus 5.5 88.7 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
2 GPT-6.1 Sol 86.4 Text only, medium Sep 2026 axisspatial.com Official leaderboard
3 GPT-6 Sol 84.9 Text only, high Sep 2026 axisspatial.com Official leaderboard
4 Claude Opus 5 84.7 Text only, high Jul 2026 axisspatial.com Official leaderboard
5 Claude Sonnet 5.5 84.4 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
6 Claude Opus 4.8 82.5 Text only, high May 2026 axisspatial.com Official leaderboard
7 Claude Haiku 5.5 82.0 Text only, xhigh Oct 2026 axisspatial.com Official leaderboard
8 Kimi K3 81.7 Text only, Reasoning Jul 2026 axisspatial.com Official leaderboard
9 GPT-5.6 Sol 81.6 Text only, high Jul 2026 axisspatial.com Official leaderboard
10 Claude Sonnet 5 80.9 Text only, high Jun 2026 axisspatial.com Official leaderboard
11 Claude Opus 4.7 80.8 Text only, high Apr 2026 axisspatial.com Official leaderboard
12 GPT-5.6 Luna 80.0 Text only, xhigh Jul 2026 axisspatial.com Official leaderboard
13 GPT-6 Luna 80.0 Text only, xhigh Sep 2026 axisspatial.com Official leaderboard
14 DeepSeek-V4-Pro 79.7 Text only, max Apr 2026 axisspatial.com Official leaderboard
15 Gemini 3.8 Flash 79.6 Text only, low Sep 2026 axisspatial.com Official leaderboard
16 DeepSeek-V4-Flash 78.7 Text only, high Apr 2026 axisspatial.com Official leaderboard
17 GLM-5.2 78.6 Text only, high Jun 2026 axisspatial.com Official leaderboard
18 GLM-5.3 78.4 Text only, max Aug 2026 axisspatial.com Official leaderboard
19 GPT-5.6 Terra 77.5 Text only, high Jul 2026 axisspatial.com Official leaderboard
20 Qwen 3.8 27B 75.8 Text only, xhigh Aug 2026 axisspatial.com Official leaderboard
21 Nemotron 3 Ultra 73.7 Text only, high Jun 2026 axisspatial.com Official leaderboard
22 GLM-5.3-Flash 72.1 Text only, low Aug 2026 axisspatial.com Official leaderboard
23 Muse Glimmer 68.4 Text only, high Aug 2026 axisspatial.com Official leaderboard
24 Claude Haiku 4.5 65.8 Text only, Reasoning Oct 2025 axisspatial.com Official leaderboard
25 Step 5 Preview 64.6 Text only, Reasoning Sep 2026 axisspatial.com Official leaderboard
26 Gemma 4 26B A4B 64.4 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
27 Gemini 3.1 Flash-Lite 63.2 Text only, high Mar 2026 axisspatial.com Official leaderboard
28 Qwen 3.6 35B-A3B 62.3 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
29 MiniMax-M3.1-Flash 61.3 Text only, max Oct 2026 axisspatial.com Official leaderboard
30 Nemotron 3.5 Super VL 59.0 Text only, Reasoning Oct 2026 axisspatial.com Official leaderboard
31 gpt-oss-120b 51.9 Text only, high Aug 2025 axisspatial.com Official leaderboard
32 Laguna XS 2.1 50.3 Text only, Reasoning Jul 2026 axisspatial.com Official leaderboard
33 glm-4.7-flash 49.6 Text only, Reasoning Jan 2026 axisspatial.com Official leaderboard
34 Mistral Large 3 44.5 Text only, Non-reasoning Dec 2025 axisspatial.com Official leaderboard
35 Nemotron 3 Nano Omni 30B-A3B 31.9 Text only, Reasoning Apr 2026 axisspatial.com Official leaderboard
36 Nemotron 3.5 Lightning 30B-A3B 27.4 Text only, Reasoning Aug 2026 axisspatial.com Official leaderboard
37 gpt-oss-20b 22.1 Text only, high Aug 2025 axisspatial.com Official leaderboard
38 Llama 3.3 70B 19.9 Text only, Non-reasoning Dec 2024 axisspatial.com Official leaderboard
39 Nemotron 3.5 Bolt E4B 16.5 Text only, Reasoning Oct 2026 axisspatial.com 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 Agent tasks, Guided workflows and Geospatial knowledge. Claude Opus 5.5 leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Agent tasks

39 models we track have a score here.

  1. 1 Claude Opus 5.5 85.0
  2. 2 GPT-6.1 Sol 84.0
  3. 3 Claude Opus 5 ↑1 80.0
  4. 4 GPT-6 Sol ↓1 80.0
  5. 5 Claude Sonnet 5.5 80.0
  6. 6 Claude Opus 4.8 76.0
  7. 7 GPT-5.6 Sol ↑2 76.0
  8. 8 Claude Haiku 5.5 ↓1 76.0
  9. 9 Kimi K3 ↓1 75.0
  10. 10 Claude Opus 4.7 ↑1 74.0

The best score, 88.7, costs $0.25 a task

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at Text only, medium comes within 2.3 of the best for $0.05 a task, 5 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Anthropic OpenAI Cost frontier One model at each effort level
0.0 20.0 40.0 60.0 80.0 100.0 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5.5, Text only, xhigh GPT-6.1 Sol, Text only, medium Claude Haiku 5.5, Text only, xhigh 0.0 20.0 40.0 60.0 80.0 100.0 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5.5, Text only, xhigh Claude Haiku 5.5, Text only, xhigh

Source: Official Spatial Intelligence Index v2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 5.5 Text only, xhigh 88.7 $0.25
GPT-6.1 Sol Text only, medium 86.4 $0.05
GPT-6 Sol Text only, high 84.9 $0.08
Claude Opus 5 Text only, high 84.7 $0.32
Claude Sonnet 5.5 Text only, xhigh 84.4 $0.11
Claude Opus 4.8 Text only, high 82.5 $0.26
Claude Haiku 5.5 Text only, xhigh 82.0 $0.02
Kimi K3 Text only, Reasoning 81.7 $0.32
GPT-5.6 Sol Text only, high 81.6 $0.21
Claude Opus 5.5 Text + vision, xhigh 81.4 $0.25
Claude Sonnet 5 Text only, high 80.9 $0.20
Claude Opus 4.7 Text only, high 80.8 $0.34
GPT-5.6 Luna Text only, xhigh 80.0 $0.02
GPT-6 Luna Text only, xhigh 80.0 $0.007
GPT-6.1 Sol Text + vision, xhigh 79.8 $0.09
DeepSeek-V4-Pro Text only, max 79.7 $0.35
Gemini 3.8 Flash Text only, low 79.6 $0.11
DeepSeek-V4-Flash Text only, high 78.7 $0.07
GLM-5.2 Text only, high 78.6 $0.22
GLM-5.3 Text only, max 78.4 $0.38
Claude Sonnet 5.5 Text + vision, xhigh 78.1 $0.11
GPT-6 Sol Text + vision, high 77.8 $0.08
GPT-5.6 Terra Text only, high 77.5 $0.10
Claude Opus 5 Text + vision, high 76.4 $0.32
Qwen 3.8 27B Text only, xhigh 75.8 $0.22
GPT-5.6 Sol Text + vision, high 75.7 $0.21
Claude Haiku 5.5 Text + vision, xhigh 74.3 $0.02
Nemotron 3 Ultra Text only, high 73.7 $0.08
Claude Opus 4.8 Text + vision, high 73.2 $0.26
GPT-5.6 Luna Text + vision, xhigh 72.8 $0.02
GPT-6 Luna Text + vision, xhigh 72.3 $0.007
GLM-5.3-Flash Text only, low 72.1 $0.05
Claude Sonnet 5 Text + vision, high 71.9 $0.20
Claude Opus 4.7 Text + vision, high 71.6 $0.34
GPT-5.6 Terra Text + vision, high 71.5 $0.10
Muse Glimmer Text only, high 68.4 $0.08
Claude Haiku 4.5 Text only, Reasoning 65.8 $0.09
Step 5 Preview Text only, Reasoning 64.6 $0.13
Gemma 4 26B A4B Text only, Reasoning 64.4 $0.02
Gemini 3.1 Flash-Lite Text only, high 63.2 $0.03
Qwen 3.6 35B-A3B Text only, Reasoning 62.3
MiniMax-M3.1-Flash Text only, max 61.3 $0.02
Nemotron 3.5 Super VL Text only, Reasoning 59.0 $0.01
Claude Haiku 4.5 Text + vision, Reasoning 52.8 $0.09
gpt-oss-120b Text only, high 51.9 $0.26
Laguna XS 2.1 Text only, Reasoning 50.3 $0.05
glm-4.7-flash Text only, Reasoning 49.6 $0.04
Mistral Large 3 Text only, Non-reasoning 44.5 $0.03
Nemotron 3 Nano Omni 30B-A3B Text only, Reasoning 31.9
Nemotron 3.5 Lightning 30B-A3B Text only, Reasoning 27.4 $0.01
gpt-oss-20b Text only, high 22.1 $0.09
Llama 3.3 70B Text only, Non-reasoning 19.9 $0.02
Nemotron 3.5 Bolt E4B Text only, Reasoning 16.5

The best score, 88.7, costs $0.25 a task

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at Text only, medium comes within 2.3 of the best for $0.05 a task, 5 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Anthropic OpenAI Cost frontier One model at each effort level
0.0 20.0 40.0 60.0 80.0 100.0 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5.5, Text only, xhigh GPT-6.1 Sol, Text only, medium Claude Haiku 5.5, Text only, xhigh 0.0 20.0 40.0 60.0 80.0 100.0 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Claude Opus 5.5, Text only, xhigh Claude Haiku 5.5, Text only, xhigh

Source: Official Spatial Intelligence Index v2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 5.5 Text only, xhigh 88.7 $0.25
GPT-6.1 Sol Text only, medium 86.4 $0.05
GPT-6 Sol Text only, high 84.9 $0.08
Claude Opus 5 Text only, high 84.7 $0.32
Claude Sonnet 5.5 Text only, xhigh 84.4 $0.11
Claude Opus 4.8 Text only, high 82.5 $0.26
Claude Haiku 5.5 Text only, xhigh 82.0 $0.02
Kimi K3 Text only, Reasoning 81.7 $0.32
GPT-5.6 Sol Text only, high 81.6 $0.21
Claude Opus 5.5 Text + vision, xhigh 81.4 $0.25
Claude Sonnet 5 Text only, high 80.9 $0.20
Claude Opus 4.7 Text only, high 80.8 $0.34
GPT-5.6 Luna Text only, xhigh 80.0 $0.02
GPT-6 Luna Text only, xhigh 80.0 $0.007
GPT-6.1 Sol Text + vision, xhigh 79.8 $0.09
DeepSeek-V4-Pro Text only, max 79.7 $0.35
Gemini 3.8 Flash Text only, low 79.6 $0.11
DeepSeek-V4-Flash Text only, high 78.7 $0.07
GLM-5.2 Text only, high 78.6 $0.22
GLM-5.3 Text only, max 78.4 $0.38
Claude Sonnet 5.5 Text + vision, xhigh 78.1 $0.11
GPT-6 Sol Text + vision, high 77.8 $0.08
GPT-5.6 Terra Text only, high 77.5 $0.10
Claude Opus 5 Text + vision, high 76.4 $0.32
Qwen 3.8 27B Text only, xhigh 75.8 $0.22
GPT-5.6 Sol Text + vision, high 75.7 $0.21
Claude Haiku 5.5 Text + vision, xhigh 74.3 $0.02
Nemotron 3 Ultra Text only, high 73.7 $0.08
Claude Opus 4.8 Text + vision, high 73.2 $0.26
GPT-5.6 Luna Text + vision, xhigh 72.8 $0.02
GPT-6 Luna Text + vision, xhigh 72.3 $0.007
GLM-5.3-Flash Text only, low 72.1 $0.05
Claude Sonnet 5 Text + vision, high 71.9 $0.20
Claude Opus 4.7 Text + vision, high 71.6 $0.34
GPT-5.6 Terra Text + vision, high 71.5 $0.10
Muse Glimmer Text only, high 68.4 $0.08
Claude Haiku 4.5 Text only, Reasoning 65.8 $0.09
Step 5 Preview Text only, Reasoning 64.6 $0.13
Gemma 4 26B A4B Text only, Reasoning 64.4 $0.02
Gemini 3.1 Flash-Lite Text only, high 63.2 $0.03
Qwen 3.6 35B-A3B Text only, Reasoning 62.3
MiniMax-M3.1-Flash Text only, max 61.3 $0.02
Nemotron 3.5 Super VL Text only, Reasoning 59.0 $0.01
Claude Haiku 4.5 Text + vision, Reasoning 52.8 $0.09
gpt-oss-120b Text only, high 51.9 $0.26
Laguna XS 2.1 Text only, Reasoning 50.3 $0.05
glm-4.7-flash Text only, Reasoning 49.6 $0.04
Mistral Large 3 Text only, Non-reasoning 44.5 $0.03
Nemotron 3 Nano Omni 30B-A3B Text only, Reasoning 31.9
Nemotron 3.5 Lightning 30B-A3B Text only, Reasoning 27.4 $0.01
gpt-oss-20b Text only, high 22.1 $0.09
Llama 3.3 70B Text only, Non-reasoning 19.9 $0.02
Nemotron 3.5 Bolt E4B Text only, Reasoning 16.5

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard 1 leader

Source: Official Spatial Intelligence Index v2 leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0 20 40 60 80 100 2025 2026 2027 0 20 40 60 80 100 2025 2026 2027

Source: Official Spatial Intelligence Index v2 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 Other

All 69 in Other
  • Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Claude Fable 5.2 64.6
  • Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
  • Vals Science Index In use Agents are scored on the equal average of BioMysteryBench, MysteryMechanism and Terminal-Bench-Science. GPT-6.2 Astra 68.4%
  • Decision Index Public v0.3 In use Decision models return probabilities over labeled options in public tasks covering knowledge, language, retrieval, tools, and arts. A chance-corrected weighted aggregate combines the task scores. Granite Switch 4.1 30B 51.3
  • SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
  • MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities. Qwen3-Embedding-8B 72.2%

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 (40 entries).
  • Pass Models scored 39 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from October 2026, for Nemotron 3.5 Bolt E4B.
  • Pass Frontier models 3 of the top 10 have a score, led by Claude Opus 5.5 (#5).
  • Note Headroom Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on axisspatial.com: 53 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.

How we check