Benchmark Almanac

DARE-Bench

Claude 3.7 Sonnet 49.3% leads since February 2026
Not in model cards

Agents write code to produce predictions from structured files. The benchmark checks predictions and adherence to modeling instructions.

The repository reports separate tables for the public subset and the full set.

Made by
Snowflake and collaborators
Released
February 2026
Kind
Data science and SQL
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Tables → Code, Actions, Tables
Interaction
Agentic
Environment
Code sandbox
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
GPT-5 #71 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
8
Models scored on its own leaderboard

Claude 3.7 Sonnet leads with 49.3% among models released by August 2025

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in August 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 Claude 3.7 Sonnet 49.3%
  2. 2 o4-mini 48.1%
  3. 3 GPT-5 45.6%
  4. 4 GPT-4.1 45.3%
  5. 5 GPT-4o Mar 2025 29.1%
  6. 6 Qwen3-32B 21%
  7. 7 Claude Sonnet 4 11%
  8. 8 Qwen3-4B 3.30%

Source: Official DARE-Bench leaderboard

#ModelScoreSettingDateSource
1 Claude 3.7 Sonnet 49.3% Feb 2025 Official leaderboard
2 o4-mini 48.1% Apr 2025 Official leaderboard
3 GPT-5 45.6% Aug 2025 Official leaderboard
4 GPT-4.1 45.3% Apr 2025 Official leaderboard
5 GPT-4o Mar 2025 29.1% Mar 2025 Official leaderboard
6 Qwen3-32B 21% Apr 2025 Official leaderboard
7 Claude Sonnet 4 11% May 2025 Official leaderboard
8 Qwen3-4B 3.30% Apr 2025 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Class-IF, Class-MM and Reg-IF. Claude 3.7 Sonnet leads 4 of them, and GPT-5 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Class-IF

8 models we track have a score here.

  1. 1 GPT-5 ↑2 69.8%
  2. 2 o4-mini 67.6%
  3. 3 Claude 3.7 Sonnet ↓2 61.5%
  4. 4 GPT-4.1 55.8%
  5. 5 GPT-4o Mar 2025 32.9%
  6. 6 Qwen3-32B 17.1%
  7. 7 Claude Sonnet 4 16.2%
  8. 8 Qwen3-4B 3.60%

Number one over time

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

Anthropic
Own leaderboard Not tested since Feb 2026

Source: Official DARE-Bench leaderboard

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
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude 3.7 Sonnet 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude 3.7 Sonnet

Source: Official DARE-Bench 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 15 months ago, in August 2025, for GPT-5. 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 official leaderboard (8 entries).
  • Pass Models scored 8 models we track.
  • Warning Newest score The newest came 15 months ago, in August 2025, for GPT-5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
  • Pass Headroom The best is 49.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 8 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