Benchmark Almanac

TRACE

GPT-5.2 63% leads since January 2026
Not in model cards

Models identify reward hacking in agent trajectories from coding environments.

The paper reports model results.

Made by
Patronus AI
Released
January 2026
Kind
Fixing real repositories
Level
Expert
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Loss of control
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
December 2025
Scores refreshed
November 20th, 2026
6
Models scored in its paper

GPT-5.2 leads with 63% among models released by December 2025

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-5.2 Contrastive, N = 10, high reasoning 63%
  2. 2 Kimi K2 Thinking Contrastive, N = 10 62%
  3. 3 Gemini 3 Pro Contrastive, N = 10 61%
  4. 4 Claude Opus 4.5 Contrastive, N = 10 59%
  5. 5 GLM-4.7 Contrastive, N = 10 59%
  6. 6 DeepSeek-V3.2 Contrastive, N = 10 58%

Source: The TRACE paper

#ModelScoreSettingDateSource
1 GPT-5.2 63% Contrastive, N = 10, high reasoning Dec 2025 Official leaderboard
2 Kimi K2 Thinking 62% Contrastive, N = 10 Nov 2025 Official leaderboard
3 Gemini 3 Pro 61% Contrastive, N = 10 Nov 2025 Official leaderboard
4 Claude Opus 4.5 59% Contrastive, N = 10 Nov 2025 Official leaderboard
5 GLM-4.7 59% Contrastive, N = 10 Dec 2025 Official leaderboard
6 DeepSeek-V3.2 58% Contrastive, N = 10 Dec 2025 Official leaderboard

More effort adds a median 18 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
GPT-5.2
Isolated, N… Contrastive…
63%
Kimi K2 Thinking
Isolated, N… Contrastive…
62%
Gemini 3 Pro
Isolated, N… Contrastive…
61%
Claude Opus 4.5
Isolated, N… Contrastive…
59%
GLM-4.7
Isolated, N… Contrastive…
59%
DeepSeek-V3.2
Isolated, N… Contrastive…
58%

Source: The TRACE paper

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.2 Contrastive, N = 10, high reasoning 63%
Kimi K2 Thinking Contrastive, N = 10 62%
Gemini 3 Pro Contrastive, N = 10 61%
Claude Opus 4.5 Contrastive, N = 10 59%
GLM-4.7 Contrastive, N = 10 59%
DeepSeek-V3.2 Contrastive, N = 10 58%
GPT-5.2 Isolated, N = 1, high reasoning 45%
Kimi K2 Thinking Isolated, N = 1 37%
Gemini 3 Pro Isolated, N = 1 35%
DeepSeek-V3.2 Isolated, N = 1 35%
GLM-4.7 Isolated, N = 1 34%
Claude Opus 4.5 Isolated, N = 1 25%

Number one over time

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

OpenAI
Benchmark paper Not tested since Jan 2026
GPT-5.2 63%

Source: The TRACE paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.2 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.2

Source: Official TRACE 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for GLM-4.7. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (6 entries).
  • Pass Models scored 6 models we track.
  • Warning Newest score The newest came 11 months ago, in December 2025, for GLM-4.7.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
  • Pass Headroom The best is 63%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on proceedings.mlr.press: 12 rows for models we track 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