Benchmark Almanac

The Aggregate Trip Outcome Prediction

GPT-5.6 Sol 69.8% leads since November 2026
Not in model cards

Models read a packing list and itinerary, then guess what happened on a weekend trip. A judge scores four answers, and relative error scores the taxi fare.

The maker ranks 27 models on five questions. Two travelers recorded their answers before testing. Nine models appear at two reasoning settings.

Released
November 2026
Kind
Commonsense
Level
Everyday
Scored
Graded by a model
Answers
Prediction
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
27
Entries on its own leaderboard, 26 models we track

5 models share the top score of 69.8% 5 models share the top score of 69.8%

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 GPT-5.6 Sol medium reasoning, 5 questions 69.8%
  2. 2 GPT-6 Astra Pro max reasoning, 5 questions 69.8%
  3. 3 Claude Opus 5.5 max reasoning, 5 questions 69.8%
  4. 4 GPT-6.1 Sol max reasoning, 5 questions 69.8%
  5. 5 GPT-6.2 Astra max reasoning, 5 questions 69.8%
  6. 6 Claude Fable 5.2 medium reasoning, 5 questions 68.7%
  7. 7 GPT-6.1 Pro Sol max reasoning, 5 questions 66.9%
  8. 8 GPT-6.2 Sol max reasoning, 5 questions 65.9%
  9. 9 Claude Fable 5.1 max reasoning, 5 questions 59.8%
  10. 10 GPT-6 Astra max reasoning, 5 questions 59.8%
  11. 11 Gemini 3.8 Flash medium reasoning, 5 questions 58.7%
  12. 12 Muse Wonder max reasoning, 5 questions 58.7%
  13. 13 GPT-6.1 Terra max reasoning, 5 questions 58.4%
  14. 14 Gemini 3.6 Flash medium reasoning, 5 questions 57.3%
  15. 15 Gemini 3.7 Flash medium reasoning, 5 questions 57.3%
  16. 16 Claude Sonnet 5.5 max reasoning, 5 questions 57.3%
  17. 17 DeepSeek V4.1 Flash 1017 max reasoning, 5 questions 55.9%
  18. 18 Gemini 4 Argon high reasoning, 5 questions 49.8%
  19. 19 Gemini 3.5 Flash medium reasoning, 5 questions 48.4%
  20. 20 GPT-5.6 Luna medium reasoning, 5 questions 47.3%
  21. 21 Gemini 3.1 Pro medium reasoning, 5 questions 45.9%
  22. 22 Gemini 3 Flash medium reasoning, 5 questions 43%
  23. 23 GPT-6 Sol medium reasoning, 5 questions 35.5%
  24. 24 Grok 4.7 xhigh reasoning, 5 questions 31.5%
  25. 25 Kimi K3.1 Pro max reasoning, 5 questions 29.8%
  26. 26 Qwen 3.8 Max prime, medium reasoning, 5 questions 23%
  27. 27 GLM-5.3-Flash medium reasoning, 5 questions 21.5%

Source: Official The Aggregate Trip Outcome Prediction leaderboard

Source: Official The Aggregate Trip Outcome Prediction leaderboard

#EntryScoreSettingReleasedRun onSource
1 GPT-5.6 Sol 69.8% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra Pro 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
3 Claude Opus 5.5 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
4 GPT-6.1 Sol 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
5 GPT-6.2 Astra 69.8% max reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
6 Claude Fable 5.2 68.7% medium reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
7 GPT-6.1 Pro Sol 66.9% max reasoning, 5 questions Nov 2026 Official leaderboard
8 GPT-6.2 Sol 65.9% max reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
9 Claude Fable 5.1 59.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
10 GPT-6 Astra 59.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
11 Gemini 3.8 Flash 58.7% medium reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
12 Muse Wonder 58.7% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
13 GPT-6.1 Terra 58.4% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
14 Gemini 3.6 Flash 57.3% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
15 Gemini 3.7 Flash 57.3% medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard
16 Claude Sonnet 5.5 57.3% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
17 DeepSeek V4.1 Flash 1017 55.9% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
18 Gemini 4 Argon 49.8% high reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
19 Gemini 3.5 Flash 48.4% medium reasoning, 5 questions May 2026 Nov 2026 Official leaderboard
20 GPT-5.6 Luna 47.3% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
21 Gemini 3.1 Pro 45.9% medium reasoning, 5 questions Feb 2026 Nov 2026 Official leaderboard
22 Gemini 3 Flash 43% medium reasoning, 5 questions Dec 2025 Nov 2026 Official leaderboard
23 GPT-6 Sol 35.5% medium reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
24 Grok 4.7 31.5% xhigh reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
25 Kimi K3.1 Pro 29.8% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
26 Qwen 3.8 Max 23% prime, medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard
27 GLM-5.3-Flash 21.5% medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GPT-5.6 Sol 69.8% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra Pro 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
3 Claude Opus 5.5 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
4 GPT-6.1 Sol 69.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
5 GPT-6.2 Astra 69.8% max reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
6 Claude Fable 5.2 68.7% medium reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
7 GPT-6.2 Sol 65.9% max reasoning, 5 questions Nov 2026 Nov 2026 Official leaderboard
8 Claude Fable 5.1 59.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
9 GPT-6 Astra 59.8% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
10 Gemini 3.8 Flash 58.7% medium reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
11 Muse Wonder 58.7% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
12 GPT-6.1 Terra 58.4% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
13 Gemini 3.6 Flash 57.3% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
14 Gemini 3.7 Flash 57.3% medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard
15 Claude Sonnet 5.5 57.3% max reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
16 DeepSeek V4.1 Flash 1017 55.9% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
17 Gemini 4 Argon 49.8% high reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
18 Gemini 3.5 Flash 48.4% medium reasoning, 5 questions May 2026 Nov 2026 Official leaderboard
19 GPT-5.6 Luna 47.3% medium reasoning, 5 questions Jul 2026 Nov 2026 Official leaderboard
20 Gemini 3.1 Pro 45.9% medium reasoning, 5 questions Feb 2026 Nov 2026 Official leaderboard
21 Gemini 3 Flash 43% medium reasoning, 5 questions Dec 2025 Nov 2026 Official leaderboard
22 GPT-6 Sol 35.5% medium reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
23 Grok 4.7 31.5% xhigh reasoning, 5 questions Sep 2026 Nov 2026 Official leaderboard
24 Kimi K3.1 Pro 29.8% max reasoning, 5 questions Oct 2026 Nov 2026 Official leaderboard
25 Qwen 3.8 Max 23% prime, medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard
26 GLM-5.3-Flash 21.5% medium reasoning, 5 questions Aug 2026 Nov 2026 Official leaderboard

More effort adds a median 9 points

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 5.5
medium reas… max reasoni…
69.8%
GPT-6.1 Sol
medium reas… max reasoni…
69.8%
GPT-6.2 Astra
medium reas…
69.8%
Claude Fable 5.2
medium reas…
68.7%
GPT-6.2 Sol
medium reas… max reasoni…
65.9%
Claude Fable 5.1
medium reas…
59.8%
GPT-6 Astra
medium reas…
59.8%
Claude Sonnet 5.5
medium reas… max reasoni…
57.3%
Grok 4.7
medium reas… xhigh reaso…
31.5%

Source: Official The Aggregate Trip Outcome Prediction leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.6 Sol medium reasoning, 5 questions 69.8%
GPT-6 Astra Pro max reasoning, 5 questions 69.8%
Claude Opus 5.5 max reasoning, 5 questions 69.8%
GPT-6.1 Sol max reasoning, 5 questions 69.8%
GPT-6.2 Astra max reasoning, 5 questions 69.8%
Claude Fable 5.2 medium reasoning, 5 questions 68.7%
GPT-6.2 Astra medium reasoning, 5 questions 68.7%
Claude Fable 5.2 max reasoning, 5 questions 68.4%
GPT-6.2 Sol max reasoning, 5 questions 65.9%
Claude Fable 5.1 max reasoning, 5 questions 59.8%
GPT-6 Astra max reasoning, 5 questions 59.8%
GPT-6.1 Sol medium reasoning, 5 questions 59.8%
Gemini 3.8 Flash medium reasoning, 5 questions 58.7%
GPT-6 Astra medium reasoning, 5 questions 58.7%
Claude Opus 5.5 medium reasoning, 5 questions 58.7%
Muse Wonder max reasoning, 5 questions 58.7%
GPT-6.1 Terra max reasoning, 5 questions 58.4%
Gemini 3.6 Flash medium reasoning, 5 questions 57.3%
Gemini 3.7 Flash medium reasoning, 5 questions 57.3%
Claude Sonnet 5.5 max reasoning, 5 questions 57.3%
DeepSeek V4.1 Flash 1017 max reasoning, 5 questions 55.9%
Claude Fable 5.1 medium reasoning, 5 questions 54.4%
Gemini 4 Argon high reasoning, 5 questions 49.8%
Gemini 3.5 Flash medium reasoning, 5 questions 48.4%
GPT-5.6 Luna medium reasoning, 5 questions 47.3%
GPT-6.2 Sol medium reasoning, 5 questions 47.3%
Gemini 3.1 Pro medium reasoning, 5 questions 45.9%
Gemini 3 Flash medium reasoning, 5 questions 43%
GPT-6 Sol medium reasoning, 5 questions 35.5%
Grok 4.7 xhigh reasoning, 5 questions 31.5%
Kimi K3.1 Pro max reasoning, 5 questions 29.8%
Qwen 3.8 Max prime, medium reasoning, 5 questions 23%
Grok 4.7 medium reasoning, 5 questions 23%
GLM-5.3-Flash medium reasoning, 5 questions 21.5%
Claude Sonnet 5.5 medium reasoning, 5 questions 16.2%

More effort adds a median 9 points

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 5.5
medium reas… max reasoni…
69.8%
GPT-6.1 Sol
medium reas… max reasoni…
69.8%
GPT-6.2 Astra
medium reas…
69.8%
Claude Fable 5.2
medium reas…
68.7%
GPT-6.2 Sol
medium reas… max reasoni…
65.9%
Claude Fable 5.1
medium reas…
59.8%
GPT-6 Astra
medium reas…
59.8%
Claude Sonnet 5.5
medium reas… max reasoni…
57.3%
Grok 4.7
medium reas… xhigh reaso…
31.5%

Source: Official The Aggregate Trip Outcome Prediction leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.6 Sol medium reasoning, 5 questions 69.8%
GPT-6 Astra Pro max reasoning, 5 questions 69.8%
Claude Opus 5.5 max reasoning, 5 questions 69.8%
GPT-6.1 Sol max reasoning, 5 questions 69.8%
GPT-6.2 Astra max reasoning, 5 questions 69.8%
Claude Fable 5.2 medium reasoning, 5 questions 68.7%
GPT-6.2 Astra medium reasoning, 5 questions 68.7%
Claude Fable 5.2 max reasoning, 5 questions 68.4%
GPT-6.2 Sol max reasoning, 5 questions 65.9%
Claude Fable 5.1 max reasoning, 5 questions 59.8%
GPT-6 Astra max reasoning, 5 questions 59.8%
GPT-6.1 Sol medium reasoning, 5 questions 59.8%
Gemini 3.8 Flash medium reasoning, 5 questions 58.7%
GPT-6 Astra medium reasoning, 5 questions 58.7%
Claude Opus 5.5 medium reasoning, 5 questions 58.7%
Muse Wonder max reasoning, 5 questions 58.7%
GPT-6.1 Terra max reasoning, 5 questions 58.4%
Gemini 3.6 Flash medium reasoning, 5 questions 57.3%
Gemini 3.7 Flash medium reasoning, 5 questions 57.3%
Claude Sonnet 5.5 max reasoning, 5 questions 57.3%
DeepSeek V4.1 Flash 1017 max reasoning, 5 questions 55.9%
Claude Fable 5.1 medium reasoning, 5 questions 54.4%
Gemini 4 Argon high reasoning, 5 questions 49.8%
Gemini 3.5 Flash medium reasoning, 5 questions 48.4%
GPT-5.6 Luna medium reasoning, 5 questions 47.3%
GPT-6.2 Sol medium reasoning, 5 questions 47.3%
Gemini 3.1 Pro medium reasoning, 5 questions 45.9%
Gemini 3 Flash medium reasoning, 5 questions 43%
GPT-6 Sol medium reasoning, 5 questions 35.5%
Grok 4.7 xhigh reasoning, 5 questions 31.5%
Kimi K3.1 Pro max reasoning, 5 questions 29.8%
Qwen 3.8 Max prime, medium reasoning, 5 questions 23%
Grok 4.7 medium reasoning, 5 questions 23%
GLM-5.3-Flash medium reasoning, 5 questions 21.5%
Claude Sonnet 5.5 medium reasoning, 5 questions 16.2%

Number one over time

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

OpenAI
Own leaderboard 1 leader
GPT-5.6 Sol 69.8%

Source: Official The Aggregate Trip Outcome Prediction 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 Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.6 Sol Gemini 3.5 Flash Gemini 3.1 Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.6 Sol Gemini 3.5 Flash

Source: Official The Aggregate Trip Outcome Prediction 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

10 of 11 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (27 entries).
  • Pass Models scored 26 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 9 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 69.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 35 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