Benchmark Almanac

HyDRA-Bench

Qwen3-8B 53.9% leads since August 2026
Not in model cards

Agents interleave database queries and document retrieval to answer questions. A model judge checks the final answer.

The paper reports accuracy over repeated runs.

Made by
Snowflake and collaborators
Released
August 2026
Kind
Data science and SQL
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Tables → Code, Actions, Text
Interaction
Agentic
Environment
APIs and tools
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Claude Opus 4.5 #62 on the capability index
Last model added
November 2025
Scores refreshed
November 21st, 2026
9
Entries in its paper, 8 models we track

Qwen3-8B leads with 53.9% among models released by November 2025 Qwen3-8B leads with 53.9% among models released by November 2025

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in November 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 Qwen3-8B TRACE-GRPO 53.9%
  2. 2 Claude Opus 4.5 50.6%
  3. 3 Qwen3-4B TRACE-GRPO 46.3%
  4. 4 GPT-5 38.4%
  5. 5 GPT-4.1 37.3%
  6. 6 Claude Sonnet 4.5 35.1%
  7. 7 GPT-4o (snapshot unspecified) 30.4%
  8. 8 Qwen3-32B 27%
  9. 9 Qwen3-14B 20.6%

Source: The HyDRA-Bench paper

#EntryScoreSettingDateSource
1 Qwen3-8B 53.9% TRACE-GRPO Apr 2025 Official leaderboard
2 Claude Opus 4.5 50.6% Nov 2025 Official leaderboard
3 Qwen3-4B 46.3% TRACE-GRPO Apr 2025 Official leaderboard
4 GPT-5 38.4% Aug 2025 Official leaderboard
5 GPT-4.1 37.3% Apr 2025 Official leaderboard
6 Claude Sonnet 4.5 35.1% Sep 2025 Official leaderboard
7 GPT-4o (snapshot unspecified) 30.4% Official leaderboard
8 Qwen3-32B 27% Apr 2025 Official leaderboard
9 Qwen3-14B 20.6% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen3-8B 53.9% TRACE-GRPO Apr 2025 Official leaderboard
2 Claude Opus 4.5 50.6% Nov 2025 Official leaderboard
3 Qwen3-4B 46.3% TRACE-GRPO Apr 2025 Official leaderboard
4 GPT-5 38.4% Aug 2025 Official leaderboard
5 GPT-4.1 37.3% Apr 2025 Official leaderboard
6 Claude Sonnet 4.5 35.1% Sep 2025 Official leaderboard
7 Qwen3-32B 27% Apr 2025 Official leaderboard
8 Qwen3-14B 20.6% Apr 2025 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as Best@1, Best@2 and Best@4. Qwen3-8B leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Best@1

8 models we track have a score here.

  1. 1 Qwen3-8B 53.7%
  2. 2 Claude Opus 4.5 51%
  3. 3 Qwen3-4B 46.3%
  4. 4 GPT-5 38.7%
  5. 5 GPT-4.1 37.8%
  6. 6 Claude Sonnet 4.5 34.8%
  7. 7 Qwen3-32B 27.4%
  8. 8 Qwen3-14B 20.7%

Number one over time

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

Qwen
Benchmark paper Not tested since Aug 2026
Qwen3-8B 53.9%

Source: The HyDRA-Bench 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% 2025 2026 Near the ceiling (85%) Qwen3-8B GPT-4.1 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Qwen3-8B GPT-4.1

Source: Official HyDRA-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 12 months ago, in November 2025, for Claude Opus 4.5. 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 benchmark’s paper (9 entries).
  • Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 12 months ago, in November 2025, for Claude Opus 4.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 4.5 (#62).
  • Pass Headroom The best is 53.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 12 rows for models we track and 1 other entry 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