DARE-Bench
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
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Claude 3.7 Sonnet 49.3%
- 2 o4-mini 48.1%
- 3 GPT-5 45.6%
- 4 GPT-4.1 45.3%
- 5 GPT-4o Mar 2025 29.1%
- 6
Qwen3-32B 21%
- 7 Claude Sonnet 4 11%
- 8
Qwen3-4B 3.30%
Source: Official DARE-Bench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 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 | | 21% | Apr 2025 | Official leaderboard | |
| 7 | Claude Sonnet 4 | 11% | May 2025 | Official leaderboard | |
| 8 | | 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 GPT-5 ↑2 69.8%
- 2 o4-mini 67.6%
- 3 Claude 3.7 Sonnet ↓2 61.5%
- 4 GPT-4.1 55.8%
- 5 GPT-4o Mar 2025 32.9%
- 6
Qwen3-32B 17.1%
- 7 Claude Sonnet 4 16.2%
- 8
Qwen3-4B 3.60%
Class-MM
8 models we track have a score here.
- 1 Claude 3.7 Sonnet 61%
- 2 o4-mini 57.9%
- 3 GPT-4.1 ↑1 57.8%
- 4 GPT-5 ↓1 43.4%
- 5 GPT-4o Mar 2025 40.5%
- 6
Qwen3-32B 30.7%
- 7 Claude Sonnet 4 18.3%
- 8
Qwen3-4B 5.23%
Reg-IF
8 models we track have a score here.
- 1 GPT-5 ↑2 57.2%
- 2 o4-mini 53.6%
- 3 GPT-4.1 ↑1 52.2%
- 4 Claude 3.7 Sonnet ↓3 46.4%
- 5 GPT-4o Mar 2025 20.3%
- 6
Qwen3-32B 15.2%
- 7 Claude Sonnet 4 15.2%
- 8
Qwen3-4B 0.72%
Reg-MM
8 models we track have a score here.
- 1 Claude 3.7 Sonnet 63.2%
- 2 GPT-4.1 ↑2 58.6%
- 3 o4-mini ↓1 57.6%
- 4 GPT-5 ↓1 56.3%
- 5 GPT-4o Mar 2025 40.6%
- 6
Qwen3-32B 35.9%
- 7 Claude Sonnet 4 11.3%
- 8
Qwen3-4B 3.29%
TS-XF
8 models we track have a score here.
- 1 Claude 3.7 Sonnet 49.9%
- 2 o4-mini 42.3%
- 3 GPT-4.1 ↑1 40.8%
- 4 GPT-5 ↓1 36.8%
- 5 GPT-4o Mar 2025 35.5%
- 6
Qwen3-32B 27%
- 7
Qwen3-4B ↑1 6.97%
- 8 Claude Sonnet 4 ↓1 4.80%
TS-CF
8 models we track have a score here.
- 1 Claude 3.7 Sonnet 13.7%
- 2 GPT-5 ↑1 10.1%
- 3 o4-mini ↓1 9.67%
- 4 GPT-4.1 6.60%
- 5 GPT-4o Mar 2025 4.77%
- 6 Claude Sonnet 4 ↑1 0.01%
- 7
Qwen3-32B ↓1 0%
- 8
Qwen3-4B 0%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
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.
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
- 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.