Benchmark Almanac

Vals Smith: palantir/blueprint

Claude Fable 5 93.2% leads since August 2026
Not in model cards

Agents modify palantir/blueprint to complete software changes from merged pull requests. Hidden tests check the changes and test for regressions.

Vals Smith generates the tasks and publishes model scores for palantir/blueprint in its public repository directory.

Made by
Vals AI
Released
August 2026
Kind
Fixing real repositories
Level
Expert
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Code sandbox
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
July 2026
Scores refreshed
November 21st, 2026
14
Entries on Vals AI’s leaderboard, 13 models we track

Claude Fable 5 leads with 93.2% among models released by July 2026 Claude Fable 5 leads with 93.2% among models released by July 2026

Best score per entry from Vals AI’s leaderboard, read on November 21st, 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.

The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Fable 5 93.2%
  2. 2 Claude Opus 4.7 88.1%
  3. 3 Claude Opus 4.8 88.1%
  4. 4 GLM-5.2 88.1%
  5. 5 GPT-5.6 Terra 88.1%
  6. 6 Claude Sonnet 5 86.4%
  7. 7 Grok 4.5 86.4%
  8. 8 GPT-5.6 Luna 86.4%
  9. 9 Kimi K3 86.4%
  10. 10 GPT-5.5 84.8%
  11. 11 Gemini 3.5 Flash 84.8%
  12. 12 GPT-5.6 Sol 84.8%
  13. 13 Gemini 3.1 Pro Preview (02/26) 79.7%
  14. 14 Claude Haiku 4.5 nonthinking 71.2%

Source: Vals AI’s leaderboard

#EntryScoreSettingDateSource
1 Claude Fable 5 93.2% Mini-SWE-agent Jun 2026 Official leaderboard
2 Claude Opus 4.7 88.1% Mini-SWE-agent Apr 2026 Official leaderboard
3 Claude Opus 4.8 88.1% Mini-SWE-agent May 2026 Official leaderboard
4 GLM-5.2 88.1% Mini-SWE-agent Jun 2026 Official leaderboard
5 GPT-5.6 Terra 88.1% Mini-SWE-agent Jul 2026 Official leaderboard
6 Claude Sonnet 5 86.4% Mini-SWE-agent Jun 2026 Official leaderboard
7 Grok 4.5 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
8 GPT-5.6 Luna 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
9 Kimi K3 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
10 GPT-5.5 84.8% Mini-SWE-agent Apr 2026 Official leaderboard
11 Gemini 3.5 Flash 84.8% Mini-SWE-agent May 2026 Official leaderboard
12 GPT-5.6 Sol 84.8% Mini-SWE-agent Jul 2026 Official leaderboard
13 Gemini 3.1 Pro Preview (02/26) 79.7% Mini-SWE-agent Official leaderboard
14 Claude Haiku 4.5 71.2% nonthinking, Mini-SWE-agent Oct 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 93.2% Mini-SWE-agent Jun 2026 Official leaderboard
2 Claude Opus 4.7 88.1% Mini-SWE-agent Apr 2026 Official leaderboard
3 Claude Opus 4.8 88.1% Mini-SWE-agent May 2026 Official leaderboard
4 GLM-5.2 88.1% Mini-SWE-agent Jun 2026 Official leaderboard
5 GPT-5.6 Terra 88.1% Mini-SWE-agent Jul 2026 Official leaderboard
6 Claude Sonnet 5 86.4% Mini-SWE-agent Jun 2026 Official leaderboard
7 Grok 4.5 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
8 GPT-5.6 Luna 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
9 Kimi K3 86.4% Mini-SWE-agent Jul 2026 Official leaderboard
10 GPT-5.5 84.8% Mini-SWE-agent Apr 2026 Official leaderboard
11 Gemini 3.5 Flash 84.8% Mini-SWE-agent May 2026 Official leaderboard
12 GPT-5.6 Sol 84.8% Mini-SWE-agent Jul 2026 Official leaderboard
13 Claude Haiku 4.5 71.2% nonthinking, Mini-SWE-agent Oct 2025 Official leaderboard

The best score, 93.2%, costs $5.33 a task

Runs on the cost frontier score higher than any run that's 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% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5 GPT-5.6 Terra GPT-5.6 Luna 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5 GPT-5.6 Terra

Source: Vals AI’s leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5 Mini-SWE-agent 93.2% $5.33
Claude Opus 4.7 Mini-SWE-agent 88.1% $3.00
Claude Opus 4.8 Mini-SWE-agent 88.1% $3.33
GLM-5.2 Mini-SWE-agent 88.1% $0.58
GPT-5.6 Terra Mini-SWE-agent 88.1% $0.39
Claude Sonnet 5 Mini-SWE-agent 86.4% $3.67
Grok 4.5 Mini-SWE-agent 86.4% $0.48
GPT-5.6 Luna Mini-SWE-agent 86.4% $0.07
Kimi K3 Mini-SWE-agent 86.4% $5.85
GPT-5.5 Mini-SWE-agent 84.8% $1.55
Gemini 3.5 Flash Mini-SWE-agent 84.8% $1.05
GPT-5.6 Sol Mini-SWE-agent 84.8% $1.74
Claude Haiku 4.5 nonthinking Mini-SWE-agent 71.2% $0.27

The best score, 93.2%, costs $5.33 a task

Runs on the cost frontier score higher than any run that's 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% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5 GPT-5.6 Terra GPT-5.6 Luna 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5 GPT-5.6 Terra

Source: Vals AI’s leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5 Mini-SWE-agent 93.2% $5.33
Claude Opus 4.7 Mini-SWE-agent 88.1% $3.00
Claude Opus 4.8 Mini-SWE-agent 88.1% $3.33
GLM-5.2 Mini-SWE-agent 88.1% $0.58
GPT-5.6 Terra Mini-SWE-agent 88.1% $0.39
Claude Sonnet 5 Mini-SWE-agent 86.4% $3.67
Grok 4.5 Mini-SWE-agent 86.4% $0.48
GPT-5.6 Luna Mini-SWE-agent 86.4% $0.07
Kimi K3 Mini-SWE-agent 86.4% $5.85
GPT-5.5 Mini-SWE-agent 84.8% $1.55
Gemini 3.5 Flash Mini-SWE-agent 84.8% $1.05
GPT-5.6 Sol Mini-SWE-agent 84.8% $1.74
Claude Haiku 4.5 nonthinking Mini-SWE-agent 71.2% $0.27

Number one over time

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

Anthropic
Vals AI leaderboard Passed 85% in Aug 2026, by Claude Fable 5

Source: Vals AI’s leaderboard

Claude Opus 4.7 on the official leaderboard passed 85% in April 2026

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 Vals AI’s leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Claude Opus 4.7 Claude Haiku 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Claude Haiku 4.5

Source: Vals AI’s 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

8 of 9 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 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 13 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from July 2026, for Kimi K3.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Fable 5 (#12).
  • Note Headroom Saturated. The best is 93.2%, past 85% since April 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on Vals AI: 13 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 21st, 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