ARCS
Models identify ambiguities in a database question and write SQL for the intended interpretation. The scorer executes the query against the database.
Megagon Labs lists 28 configurations of 23 models. Its 311 test cases cover 101 questions across six databases.
- Made by
- Megagon Labs and collaborators
- Released
- October 2026
- Kind
- Data science and SQL
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Sol #13 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-5 leads with 57.9% among models released by September 2026
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. Every run is in the next chart.
The newest model with a score here came out in September 2026, 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-6.1 Sol
- and 15 more
- 57.9 GPT-5
- 51.8 GPT-6 Sol
- 46.3 GPT-6 Luna
- 44.4 GPT-5 mini
- 44.0 o4-mini
- 44.0
Gemini 3 Pro
- 43.7 Claude Sonnet 4.5
- 38.6 Claude Opus 4.5
- 30.9
Gemini 2.5 Pro
- 29.9 GPT-4.1
- 29.3 GPT-5 nano
- 28.6 Claude Haiku 4.5
- 27.6
Gemini 2.5 Flash
- 26.1 gpt-oss-120b
- 23.5
DeepSeek-V3.1
- 23.1
DeepSeek-R1
- 21.9 GPT-4.1 mini
- 20.3
Qwen3-235B-A22B-Instruct
- 19.3 Kimi K2 Thinking
- 15.8
Qwen3-Coder-480B-A35B
- 7.40 gpt-oss-20b
- 7.07 GPT-4.1 nano
- 5.79
Qwen3-8B
- 1 GPT-5 medium 57.9%
- 2 GPT-6 Sol medium 51.8%
- 3 GPT-6 Luna medium 46.3%
- 4 GPT-5 mini medium 44.4%
- 5 o4-mini high 44%
- 6
Gemini 3 Pro high 44%
- 7 Claude Sonnet 4.5 high 43.7%
- 8 Claude Opus 4.5 high 38.6%
- 9
Gemini 2.5 Pro Jun 2025 30.9%
- 10 GPT-4.1 29.9%
- 11 GPT-5 nano medium 29.3%
- 12 Claude Haiku 4.5 high 28.6%
- 13
Gemini 2.5 Flash Sep 2025 27.6%
- 14 gpt-oss-120b 26.1%
- 15
DeepSeek-V3.1 23.5%
- 16
DeepSeek-R1 May 2025 23.1%
- 17 GPT-4.1 mini 21.9%
- 18
Qwen3-235B-A22B-Instruct Jul 2025 20.3%
- 19 Kimi K2 Thinking 19.3%
- 20
Qwen3-Coder-480B-A35B 15.8%
- 21 gpt-oss-20b 7.40%
- 22 GPT-4.1 nano 7.07%
- 23
Qwen3-8B 5.79%
Source: Official ARCS leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 57.9% | medium | Aug 2025 | Official leaderboard |
| 2 | GPT-6 Sol | 51.8% | medium | Sep 2026 | Official leaderboard |
| 3 | GPT-6 Luna | 46.3% | medium | Sep 2026 | Official leaderboard |
| 4 | GPT-5 mini | 44.4% | medium | Aug 2025 | Official leaderboard |
| 5 | o4-mini | 44% | high | Apr 2025 | Official leaderboard |
| 6 | | 44% | high | Nov 2025 | Official leaderboard |
| 7 | Claude Sonnet 4.5 | 43.7% | high | Sep 2025 | Official leaderboard |
| 8 | Claude Opus 4.5 | 38.6% | high | Nov 2025 | Official leaderboard |
| 9 | | 30.9% | Jun 2025 | Official leaderboard | |
| 10 | GPT-4.1 | 29.9% | Apr 2025 | Official leaderboard | |
| 11 | GPT-5 nano | 29.3% | medium | Aug 2025 | Official leaderboard |
| 12 | Claude Haiku 4.5 | 28.6% | high | Oct 2025 | Official leaderboard |
| 13 | | 27.6% | Sep 2025 | Official leaderboard | |
| 14 | gpt-oss-120b | 26.1% | Aug 2025 | Official leaderboard | |
| 15 | | 23.5% | Aug 2025 | Official leaderboard | |
| 16 | | 23.1% | May 2025 | Official leaderboard | |
| 17 | GPT-4.1 mini | 21.9% | Apr 2025 | Official leaderboard | |
| 18 | | 20.3% | Jul 2025 | Official leaderboard | |
| 19 | Kimi K2 Thinking | 19.3% | Nov 2025 | Official leaderboard | |
| 20 | | 15.8% | Jul 2025 | Official leaderboard | |
| 21 | gpt-oss-20b | 7.40% | Aug 2025 | Official leaderboard | |
| 22 | GPT-4.1 nano | 7.07% | Apr 2025 | Official leaderboard | |
| 23 | | 5.79% | Apr 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Full Recall, Perfect and EX disamb. Each ranks models on one part of the test. GPT-5 leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Full Recall
23 models we track have a score here.
- 1 GPT-5 61.1%
- 2 GPT-5 mini ↑2 42.1%
- 3 GPT-6 Sol ↓1 40.8%
- 4 GPT-6 Luna ↓1 31.2%
- 5 o4-mini 30.6%
- 6
Gemini 3 Pro 26.4%
- 7 Claude Sonnet 4.5 23.5%
- 8 Claude Opus 4.5 22.5%
- 9
Gemini 2.5 Pro Jun 2025 20.9%
- 10 Claude Haiku 4.5 ↑2 17.7%
Perfect
23 models we track have a score here.
- 1
Gemini 3 Pro ↑5 13.8%
- 2
Gemini 2.5 Flash Sep 2025 ↑11 10.6%
- 3 GPT-6 Luna 10.6%
- 4
Gemini 2.5 Pro Jun 2025 ↑5 9.65%
- 5 GPT-6 Sol ↓3 9.32%
- 6 o4-mini ↓1 8.36%
- 7 Claude Haiku 4.5 ↑5 8.04%
- 8 Claude Opus 4.5 8.04%
- 9 GPT-4.1 ↑1 7.40%
- 10 Claude Sonnet 4.5 ↓3 7.40%
EX disamb
23 models we track have a score here.
- 1 GPT-6 Sol ↑1 74.6%
- 2 GPT-5 ↓1 68.8%
- 3 GPT-6 Luna 68.2%
- 4 Claude Opus 4.5 ↑4 67.8%
- 5
Gemini 3 Pro ↑1 65.3%
- 6 o4-mini ↓1 65%
- 7 GPT-5 mini ↓3 63%
- 8 Claude Sonnet 4.5 ↓1 57.9%
- 9 GPT-4.1 ↑1 56.3%
- 10 gpt-oss-120b ↑4 52.1%
The best score, 57.9%, costs $0.09 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official ARCS leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5 | medium | 57.9% | $0.09 | ||
| GPT-5 | high | 57.6% | $0.16 | ||
| GPT-6 Sol | medium | 51.8% | $0.04 | ||
| GPT-5 | low | 48.5% | $0.04 | ||
| GPT-6 Luna | medium | 46.3% | $0.006 | ||
| GPT-5 mini | medium | 44.4% | $0.01 | ||
| o4-mini | high | 44% | $0.06 | ||
| high | 44% | $0.14 | |||
| Claude Sonnet 4.5 | high | 43.7% | $0.09 | ||
| o4-mini | medium | 42.4% | $0.03 | ||
| Claude Opus 4.5 | high | 38.6% | $0.15 | ||
| GPT-5 | minimal | 37.6% | $0.02 | ||
| o4-mini | low | 36% | $0.02 | ||
| 30.9% | $0.06 | ||||
| GPT-4.1 | 29.9% | $0.03 | |||
| GPT-5 nano | medium | 29.3% | $0.005 | ||
| Claude Haiku 4.5 | high | 28.6% | $0.03 | ||
| 27.6% | $0.01 | ||||
| gpt-oss-120b | 26.1% | $0.003 | |||
| 23.5% | $0.01 | ||||
| 23.1% | $0.04 | ||||
| GPT-4.1 mini | 21.9% | $0.007 | |||
| 20.3% | $0.02 | ||||
| Kimi K2 Thinking | 19.3% | $0.03 | |||
| 15.8% | $0.03 | ||||
| gpt-oss-20b | 7.40% | $0.0003 | |||
| GPT-4.1 nano | 7.07% | $0.006 | |||
| 5.79% | $0.009 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official ARCS 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 ARCS 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
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (23 entries).
- Pass Models scored 23 models we track.
- Pass Newest score The newest is from September 2026, for GPT-6 Luna.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-6 Sol (#13).
- Pass Headroom The best is 57.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on megagonlabs.github.io: 28 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.