Benchmark Almanac

Augment Prism multi-turn coding benchmark

Prism (GPT + Kimi) 0.30 tops its leaderboard GPT-5.5 0.21 leads the models we track
Not in model cards

Coding agents follow a queued conversation and edit a repository. A model compares the final changes with the original pull request.

Augment publishes scores and costs for seven configurations, including five standalone models. Each run covers 25 tasks.

Made by
Augment Code
Released
May 2026
Kind
Fixing real repositories
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Agentic
Environment
Terminal
Items from
Real work and use
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 21st, 2026
7
Entries in its paper, 5 models we track

Prism (GPT + Kimi) tops the leaderboard with 0.30 GPT-5.5 leads with 0.21 among models released by April 2026

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Average overall score in Augment Prism multi-turn coding evaluation. 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. The best model we track is GPT-5.5, at 0.21. This view shows only models we track, each at its best.

The newest model with a score here came out in April 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 Prism (GPT + Kimi) 0.30
  2. 2 GPT-5.5 0.21
  3. 3 Prism (Claude + Gemini) 0.11
  4. 4 Claude Opus 4.7 0.08
  5. 5 Claude Sonnet 4.6 -0.11
  6. 6 Kimi K2.6 -0.23
  7. 7 Claude Opus 4.6 -0.37

Source: The Augment Prism multi-turn coding benchmark paper

#EntryScoreSettingDateSource
1 Prism (GPT + Kimi) 0.30 Official leaderboard
2 GPT-5.5 0.21 Apr 2026 Official leaderboard
3 Prism (Claude + Gemini) 0.11 Official leaderboard
4 Claude Opus 4.7 0.08 Apr 2026 Official leaderboard
5 Claude Sonnet 4.6 -0.11 Feb 2026 Official leaderboard
6 Kimi K2.6 -0.23 Apr 2026 Official leaderboard
7 Claude Opus 4.6 -0.37 Feb 2026 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.5 0.21 Apr 2026 Official leaderboard
2 Claude Opus 4.7 0.08 Apr 2026 Official leaderboard
3 Claude Sonnet 4.6 -0.11 Feb 2026 Official leaderboard
4 Kimi K2.6 -0.23 Apr 2026 Official leaderboard
5 Claude Opus 4.6 -0.37 Feb 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
Benchmark paper Not tested since May 2026
GPT-5.5 0.21

Source: The Augment Prism multi-turn coding benchmark 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
-0.40 -0.20 0.00 0.20 0.40 2026 -0.40 -0.20 0.00 0.20 0.40 2026

Source: Official Augment Prism multi-turn coding benchmark 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 Newest score check. The newest came 7 months ago, in April 2026, for GPT-5.5. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (7 entries).
  • Pass Models scored 5 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 7 months ago, in April 2026, for GPT-5.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on augmentcode.com: 5 rows for models we track and 2 other entries 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