Benchmark Almanac

ts-bench

Claude Sonnet 4.6 80% leads since February 2026
Not in model cards

Coding agents such as Claude Code, Codex and Gemini CLI solve TypeScript tasks, and tests decide pass or fail. Version 1 uses 25 Exercism practice exercises. Version 2 uses real tasks from a large TypeScript monorepo, taken from SWE-Lancer.

The author calls the numbers directional, not lab-grade. Results are published as GitHub workflow runs and releases. Version 1 is frozen at the v1-final tag. About 243 GitHub stars.

Released
June 2025
Kind
Function-level problems
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-5.4 #27 on the capability index
Last model added
March 2026
Scores refreshed
November 12th, 2026
8
Entries on its own leaderboard, 7 models we track

Claude Sonnet 4.6 leads with 80% among models released by March 2026

Best score per entry from the benchmark's own leaderboard, read on November 12th, 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.

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

  1. 80.0 Claude Sonnet 4.6
  2. 60.0 Gemini 3.1 Pro
  3. 60.0 GPT-5.4
  4. 40.0 Claude Opus 4.6
  5. 40.0 gemini-2.5-flash (snapshot unspecified)
  6. 20.0 Claude Haiku 4.5
  7. 20.0 Gemini 3 Flash
  8. 0.0 GPT-5.4 Mini
  1. 1 Claude Sonnet 4.6 80%
  2. 2 Gemini 3.1 Pro 60%
  3. 3 GPT-5.4 60%
  4. 4 Claude Opus 4.6 40%
  5. 5 gemini-2.5-flash (snapshot unspecified) 40%
  6. 6 Claude Haiku 4.5 20%
  7. 7 Gemini 3 Flash 20%
  8. 8 GPT-5.4 Mini 0%

Source: Official ts-bench leaderboard

#EntryScoreSettingDateSource
1 Claude Sonnet 4.6 80% GitHub Copilot CLI Feb 2026 Official leaderboard
2 Gemini 3.1 Pro 60% Gemini CLI Feb 2026 Official leaderboard
3 GPT-5.4 60% Codex CLI Mar 2026 Official leaderboard
4 Claude Opus 4.6 40% GitHub Copilot CLI Feb 2026 Official leaderboard
5 gemini-2.5-flash (snapshot unspecified) 40% Gemini CLI Apr 2026 Official leaderboard
6 Claude Haiku 4.5 20% Claude Code Oct 2025 Official leaderboard
7 Gemini 3 Flash 20% Gemini CLI Dec 2025 Official leaderboard
8 GPT-5.4 Mini 0% Codex CLI Mar 2026 Official leaderboard

3 models have held number one on the official leaderboard since its release in June 2025

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

Anthropic
Own leaderboard Not tested since Mar 2026
Claude Sonnet 4.6 80%

Source: Official ts-bench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Sonnet 4.6 Claude Opus 4.6 Claude Haiku 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Sonnet 4.6 Claude Opus 4.6

Source: Official ts-bench leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

Versions

Replaces ts-bench v1

More in Coding

All 282 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