Benchmark Almanac

Prompt to Product

GPT-5.6 Sol 98.2% leads since October 2026
Not in model cards

Agents build web applications from product briefs. Browser tests exercise features such as checkout arithmetic, saved filters, keyboard accessibility, and mobile layouts.

Kaggle publishes scores for 43 distinct model versions.

Made by
Shash
Released
October 2026
Kind
Web and app front ends
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Code, Actions
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
40
Entries on its own leaderboard, 38 models we track

3 models share the top score of 98.2% 3 models share the top score of 98.2%

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. This view shows only models we track, each at its best.

  1. 1 GPT-5.6 Sol 98.2%
  2. 2 Claude Sonnet 5.5 98.2%
  3. 3 Gemini 4 Argon 98.2%
  4. 4 GPT-5.5 98%
  5. 5 Claude Haiku 5.5 98%
  6. 6 GPT-6 Luna 97.5%
  7. 7 Gemini 3 Flash 97.3%
  8. 8 GPT-6.1 Sol 96.3%
  9. 9 Gemma 4 31B IT 96.2%
  10. 10 Gemini 3.6 Flash 95.5%
  11. 11 Claude Opus 4.7 95%
  12. 12 Gemini 3.1 Pro 94.8%
  13. 13 GPT-6 Astra 94.8%
  14. 14 Claude Opus 4.6 94.7%
  15. 15 Claude Opus 4.5 94.5%
  16. 16 GPT-6 Sol 94.2%
  17. 17 Gemini 3.8 Flash 94%
  18. 18 GPT-5.6 Terra 93.3%
  19. 19 Claude Haiku 4.5 92.8%
  20. 20 GPT-5.4 92.8%
  21. 21 Claude Opus 5.5 92.2%
  22. 22 Claude Opus 5 91.3%
  23. 23 Claude Sonnet 5 91%
  24. 24 Gemini 3.5 Flash-Lite 91%
  25. 25 GPT-5.6 Luna 90.7%
  26. 26 Claude Opus 4.8 90.2%
  27. 27 Gemini 2.5 Pro Jun 2025 88.3%
  28. 28 GPT-5.4 Nano 88.3%
  29. 29 gpt-oss-20b 87.2%
  30. 30 GLM-5 85%
  31. 31 Gemma 4 26B A4B 84.8%
  32. 32 Qwen3-Coder-480B-A35B 84%
  33. 33 Gemini 2.5 Flash Sep 2025 82.7%
  34. 34 Qwen 3 Next 80B Instruct 82.5%
  35. 35 Qwen 3 235B A22B Instruct 2506 82.3%
  36. 36 Claude Sonnet 4.6 79%
  37. 37 gpt-oss-120b 74.8%
  38. 38 GPT-5.4 Mini 74%
  39. 39 DeepSeek-R1 May 2025 73.8%
  40. 40 Gemini 3.1 Flash-Lite 70.5%

Source: Official Prompt to Product leaderboard

Source: Official Prompt to Product leaderboard

#EntryScoreSettingReleasedRun onSource
1 GPT-5.6 Sol 98.2% Jul 2026 Oct 2026 Official leaderboard
2 Claude Sonnet 5.5 98.2% Sep 2026 Oct 2026 Official leaderboard
3 Gemini 4 Argon 98.2% Sep 2026 Oct 2026 Official leaderboard
4 GPT-5.5 98% Apr 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 98% Oct 2026 Oct 2026 Official leaderboard
6 GPT-6 Luna 97.5% Sep 2026 Oct 2026 Official leaderboard
7 Gemini 3 Flash 97.3% Dec 2025 Oct 2026 Official leaderboard
8 GPT-6.1 Sol 96.3% Sep 2026 Oct 2026 Official leaderboard
9 Gemma 4 31B IT 96.2% Apr 2026 Oct 2026 Official leaderboard
10 Gemini 3.6 Flash 95.5% Jul 2026 Oct 2026 Official leaderboard
11 Claude Opus 4.7 95% Apr 2026 Oct 2026 Official leaderboard
12 Gemini 3.1 Pro 94.8% Feb 2026 Oct 2026 Official leaderboard
13 GPT-6 Astra 94.8% Sep 2026 Oct 2026 Official leaderboard
14 Claude Opus 4.6 94.7% Feb 2026 Oct 2026 Official leaderboard
15 Claude Opus 4.5 94.5% Nov 2025 Oct 2026 Official leaderboard
16 GPT-6 Sol 94.2% Sep 2026 Oct 2026 Official leaderboard
17 Gemini 3.8 Flash 94% Sep 2026 Oct 2026 Official leaderboard
18 GPT-5.6 Terra 93.3% Jul 2026 Oct 2026 Official leaderboard
19 Claude Haiku 4.5 92.8% Oct 2025 Oct 2026 Official leaderboard
20 GPT-5.4 92.8% Mar 2026 Oct 2026 Official leaderboard
21 Claude Opus 5.5 92.2% Sep 2026 Oct 2026 Official leaderboard
22 Claude Opus 5 91.3% Jul 2026 Oct 2026 Official leaderboard
23 Claude Sonnet 5 91% Jun 2026 Oct 2026 Official leaderboard
24 Gemini 3.5 Flash-Lite 91% Jul 2026 Oct 2026 Official leaderboard
25 GPT-5.6 Luna 90.7% Jul 2026 Oct 2026 Official leaderboard
26 Claude Opus 4.8 90.2% May 2026 Oct 2026 Official leaderboard
27 Gemini 2.5 Pro Jun 2025 88.3% Jun 2025 Oct 2026 Official leaderboard
28 GPT-5.4 Nano 88.3% Mar 2026 Oct 2026 Official leaderboard
29 gpt-oss-20b 87.2% Aug 2025 Oct 2026 Official leaderboard
30 GLM-5 85% Feb 2026 Oct 2026 Official leaderboard
31 Gemma 4 26B A4B 84.8% Apr 2026 Oct 2026 Official leaderboard
32 Qwen3-Coder-480B-A35B 84% Jul 2025 Oct 2026 Official leaderboard
33 Gemini 2.5 Flash Sep 2025 82.7% Sep 2025 Oct 2026 Official leaderboard
34 Qwen 3 Next 80B Instruct 82.5% Oct 2026 Official leaderboard
35 Qwen 3 235B A22B Instruct 2506 82.3% Oct 2026 Official leaderboard
36 Claude Sonnet 4.6 79% Feb 2026 Oct 2026 Official leaderboard
37 gpt-oss-120b 74.8% Aug 2025 Oct 2026 Official leaderboard
38 GPT-5.4 Mini 74% Mar 2026 Oct 2026 Official leaderboard
39 DeepSeek-R1 May 2025 73.8% May 2025 Oct 2026 Official leaderboard
40 Gemini 3.1 Flash-Lite 70.5% Mar 2026 Oct 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GPT-5.6 Sol 98.2% Jul 2026 Oct 2026 Official leaderboard
2 Claude Sonnet 5.5 98.2% Sep 2026 Oct 2026 Official leaderboard
3 Gemini 4 Argon 98.2% Sep 2026 Oct 2026 Official leaderboard
4 GPT-5.5 98% Apr 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 98% Oct 2026 Oct 2026 Official leaderboard
6 GPT-6 Luna 97.5% Sep 2026 Oct 2026 Official leaderboard
7 Gemini 3 Flash 97.3% Dec 2025 Oct 2026 Official leaderboard
8 GPT-6.1 Sol 96.3% Sep 2026 Oct 2026 Official leaderboard
9 Gemma 4 31B IT 96.2% Apr 2026 Oct 2026 Official leaderboard
10 Gemini 3.6 Flash 95.5% Jul 2026 Oct 2026 Official leaderboard
11 Claude Opus 4.7 95% Apr 2026 Oct 2026 Official leaderboard
12 Gemini 3.1 Pro 94.8% Feb 2026 Oct 2026 Official leaderboard
13 GPT-6 Astra 94.8% Sep 2026 Oct 2026 Official leaderboard
14 Claude Opus 4.6 94.7% Feb 2026 Oct 2026 Official leaderboard
15 Claude Opus 4.5 94.5% Nov 2025 Oct 2026 Official leaderboard
16 GPT-6 Sol 94.2% Sep 2026 Oct 2026 Official leaderboard
17 Gemini 3.8 Flash 94% Sep 2026 Oct 2026 Official leaderboard
18 GPT-5.6 Terra 93.3% Jul 2026 Oct 2026 Official leaderboard
19 Claude Haiku 4.5 92.8% Oct 2025 Oct 2026 Official leaderboard
20 GPT-5.4 92.8% Mar 2026 Oct 2026 Official leaderboard
21 Claude Opus 5.5 92.2% Sep 2026 Oct 2026 Official leaderboard
22 Claude Opus 5 91.3% Jul 2026 Oct 2026 Official leaderboard
23 Claude Sonnet 5 91% Jun 2026 Oct 2026 Official leaderboard
24 Gemini 3.5 Flash-Lite 91% Jul 2026 Oct 2026 Official leaderboard
25 GPT-5.6 Luna 90.7% Jul 2026 Oct 2026 Official leaderboard
26 Claude Opus 4.8 90.2% May 2026 Oct 2026 Official leaderboard
27 Gemini 2.5 Pro Jun 2025 88.3% Jun 2025 Oct 2026 Official leaderboard
28 GPT-5.4 Nano 88.3% Mar 2026 Oct 2026 Official leaderboard
29 gpt-oss-20b 87.2% Aug 2025 Oct 2026 Official leaderboard
30 GLM-5 85% Feb 2026 Oct 2026 Official leaderboard
31 Gemma 4 26B A4B 84.8% Apr 2026 Oct 2026 Official leaderboard
32 Qwen3-Coder-480B-A35B 84% Jul 2025 Oct 2026 Official leaderboard
33 Gemini 2.5 Flash Sep 2025 82.7% Sep 2025 Oct 2026 Official leaderboard
34 Claude Sonnet 4.6 79% Feb 2026 Oct 2026 Official leaderboard
35 gpt-oss-120b 74.8% Aug 2025 Oct 2026 Official leaderboard
36 GPT-5.4 Mini 74% Mar 2026 Oct 2026 Official leaderboard
37 DeepSeek-R1 May 2025 73.8% May 2025 Oct 2026 Official leaderboard
38 Gemini 3.1 Flash-Lite 70.5% Mar 2026 Oct 2026 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Passed 85% in Oct 2026, by GPT-5.6 Sol
GPT-5.6 Sol 98.2%

Source: Official Prompt to Product leaderboard

Gemini 2.5 Pro on the official leaderboard passed 85% in June 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.6 Sol Gemini 3 Flash Claude Haiku 4.5 Gemini 2.5 Pro DeepSeek-R1 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.6 Sol Gemini 2.5 Pro

Source: Official Prompt to Product 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 Coding

All 523 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471

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 38 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Saturated. The best is 98.2%, past 85% since June 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 38 rows for models we track and 2 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check