DualChem
Models answer chemistry questions written by experts. The researchers report answer accuracy and assess whether models recognize possible misuse.
Scale AI developed the 600-question benchmark under its NIST research agreement and evaluated more than 30 models. Higher refers to answer accuracy.
- Released
- October 2026
- Kind
- Dangerous capabilities
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Measures
- Capability
- Risk
- CBRN
- Subject
- Chemical sciences
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 21st, 2026
GPT-5.6 Sol leads with 67.3% GPT-5.6 Sol leads with 67.3%
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.
- 67.3 GPT-5.6 Sol
- 62.7 GPT-6 Astra
- 61.7 GPT-6.1 Sol
- 60.3 GPT-5.6 Terra
- 60.0
Muse Wonder
- 59.8 GPT-5.2
- 59.8
Muse Spark 1.3
- 59.2 GPT-5.6 Luna
- 58.3 Claude Opus 4.8
- 58.0 Claude Sonnet 5.5
- 57.5 o3
- 56.8
Muse Spark Open
- 56.7 Claude Sonnet 5
- 55.2
Gemini 4 Argon
- 53.3 Claude Opus 4.5
- 52.5
Gemini 3 Flash
- 52.3
Gemini 2.5 Pro
- 52.3
DeepSeek-V4-Pro
- 52.2 o4-mini
- 50.2 Claude Opus 5.5
- 49.8 Claude Sonnet 4.5
- 48.8 Claude Opus 4.1
- 48.7
Gemini 3.5 Flash
- 45.7
Gemini 3.1 Pro
- 45.2
Llama 3.3 70B
- 45.0 o3-mini
- 44.5
DeepSeek-V3
- 43.3
Gemini 3 Pro
- 43.3 Claude Fable 5
- 42.8 Claude Fable 5.1
- 41.2 Qwen3 235B
- 40.2
Qwen3-32B
- 23.7
Llama 3.1-8B
- 1 GPT-5.6 Sol 67.3%
- 2 GPT-6 Astra 62.7%
- 3 GPT-6.1 Sol 61.7%
- 4 GPT-5.6 Terra 60.3%
- 5
Muse Wonder 60%
- 6 GPT-5.2 59.8%
- 7
Muse Spark 1.3 59.8%
- 8 GPT-5.6 Luna 59.2%
- 9 Claude Opus 4.8 58.3%
- 10 Claude Sonnet 5.5 58%
- 11 o3 57.5%
- 12
Muse Spark Open 56.8%
- 13 Claude Sonnet 5 56.7%
- 14
Gemini 4 Argon 55.2%
- 15 Claude Opus 4.5 53.3%
- 16
Gemini 3 Flash 52.5%
- 17
Gemini 2.5 Pro Jun 2025 52.3%
- 18
DeepSeek-V4-Pro 52.3%
- 19 o4-mini 52.2%
- 20 Claude Opus 5.5 50.2%
- 21 Claude Sonnet 4.5 49.8%
- 22 Claude Opus 4.1 48.8%
- 23
Gemini 3.5 Flash 48.7%
- 24
Gemini 3.1 Pro 45.7%
- 25
Llama 3.3 70B 45.2%
- 26 o3-mini 45%
- 27
DeepSeek-V3 Mar 2025 44.5%
- 28
Gemini 3 Pro 43.3%
- 29 Claude Fable 5 43.3%
- 30 Claude Fable 5.1 42.8%
- 31 Qwen3 235B 41.2%
- 32
Qwen3-32B 40.2%
- 33
Llama 3.1-8B 23.7%
Source: The DualChem paper
- 67.3 GPT-5.6 Sol
- 62.7 GPT-6 Astra
- 61.7 GPT-6.1 Sol
- 60.3 GPT-5.6 Terra
- 60.0
Muse Wonder
- 59.8 GPT-5.2
- 59.8
Muse Spark 1.3
- 59.2 GPT-5.6 Luna
- 58.3 Claude Opus 4.8
- 58.0 Claude Sonnet 5.5
- 57.5 o3
- 56.8
Muse Spark Open
- 56.7 Claude Sonnet 5
- 55.2
Gemini 4 Argon
- 53.3 Claude Opus 4.5
- 52.5
Gemini 3 Flash
- 52.3
Gemini 2.5 Pro
- 52.3
DeepSeek-V4-Pro
- 52.2 o4-mini
- 50.2 Claude Opus 5.5
- 49.8 Claude Sonnet 4.5
- 48.8 Claude Opus 4.1
- 48.7
Gemini 3.5 Flash
- 45.7
Gemini 3.1 Pro
- 45.2
Llama 3.3 70B
- 45.0 o3-mini
- 44.5
DeepSeek-V3
- 43.3
Gemini 3 Pro
- 43.3 Claude Fable 5
- 42.8 Claude Fable 5.1
- 40.2
Qwen3-32B
- 23.7
Llama 3.1-8B
- 1 GPT-5.6 Sol 67.3%
- 2 GPT-6 Astra 62.7%
- 3 GPT-6.1 Sol 61.7%
- 4 GPT-5.6 Terra 60.3%
- 5
Muse Wonder 60%
- 6 GPT-5.2 59.8%
- 7
Muse Spark 1.3 59.8%
- 8 GPT-5.6 Luna 59.2%
- 9 Claude Opus 4.8 58.3%
- 10 Claude Sonnet 5.5 58%
- 11 o3 57.5%
- 12
Muse Spark Open 56.8%
- 13 Claude Sonnet 5 56.7%
- 14
Gemini 4 Argon 55.2%
- 15 Claude Opus 4.5 53.3%
- 16
Gemini 3 Flash 52.5%
- 17
Gemini 2.5 Pro Jun 2025 52.3%
- 18
DeepSeek-V4-Pro 52.3%
- 19 o4-mini 52.2%
- 20 Claude Opus 5.5 50.2%
- 21 Claude Sonnet 4.5 49.8%
- 22 Claude Opus 4.1 48.8%
- 23
Gemini 3.5 Flash 48.7%
- 24
Gemini 3.1 Pro 45.7%
- 25
Llama 3.3 70B 45.2%
- 26 o3-mini 45%
- 27
DeepSeek-V3 Mar 2025 44.5%
- 28
Gemini 3 Pro 43.3%
- 29 Claude Fable 5 43.3%
- 30 Claude Fable 5.1 42.8%
- 31
Qwen3-32B 40.2%
- 32
Llama 3.1-8B 23.7%
Source: The DualChem paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.6 Sol | 67.3% | Jul 2026 | Official leaderboard | |
| 2 | GPT-6 Astra | 62.7% | Sep 2026 | Official leaderboard | |
| 3 | GPT-6.1 Sol | 61.7% | Sep 2026 | Official leaderboard | |
| 4 | GPT-5.6 Terra | 60.3% | Jul 2026 | Official leaderboard | |
| 5 | | 60% | Oct 2026 | Official leaderboard | |
| 6 | GPT-5.2 | 59.8% | Dec 2025 | Official leaderboard | |
| 7 | | 59.8% | Sep 2026 | Official leaderboard | |
| 8 | GPT-5.6 Luna | 59.2% | Jul 2026 | Official leaderboard | |
| 9 | Claude Opus 4.8 | 58.3% | May 2026 | Official leaderboard | |
| 10 | Claude Sonnet 5.5 | 58% | Sep 2026 | Official leaderboard | |
| 11 | o3 | 57.5% | Apr 2025 | Official leaderboard | |
| 12 | | 56.8% | Oct 2026 | Official leaderboard | |
| 13 | Claude Sonnet 5 | 56.7% | Jun 2026 | Official leaderboard | |
| 14 | | 55.2% | Sep 2026 | Official leaderboard | |
| 15 | Claude Opus 4.5 | 53.3% | Nov 2025 | Official leaderboard | |
| 16 | | 52.5% | Dec 2025 | Official leaderboard | |
| 17 | | 52.3% | Jun 2025 | Official leaderboard | |
| 18 | | 52.3% | Apr 2026 | Official leaderboard | |
| 19 | o4-mini | 52.2% | Apr 2025 | Official leaderboard | |
| 20 | Claude Opus 5.5 | 50.2% | Sep 2026 | Official leaderboard | |
| 21 | Claude Sonnet 4.5 | 49.8% | Sep 2025 | Official leaderboard | |
| 22 | Claude Opus 4.1 | 48.8% | Aug 2025 | Official leaderboard | |
| 23 | | 48.7% | May 2026 | Official leaderboard | |
| 24 | | 45.7% | Feb 2026 | Official leaderboard | |
| 25 | | 45.2% | Dec 2024 | Official leaderboard | |
| 26 | o3-mini | 45% | Jan 2025 | Official leaderboard | |
| 27 | | 44.5% | Mar 2025 | Official leaderboard | |
| 28 | | 43.3% | Nov 2025 | Official leaderboard | |
| 29 | Claude Fable 5 | 43.3% | Jun 2026 | Official leaderboard | |
| 30 | Claude Fable 5.1 | 42.8% | Sep 2026 | Official leaderboard | |
| 31 | Qwen3 235B | 41.2% | Official leaderboard | ||
| 32 | | 40.2% | Apr 2025 | Official leaderboard | |
| 33 | | 23.7% | Jul 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.6 Sol | 67.3% | Jul 2026 | Official leaderboard | |
| 2 | GPT-6 Astra | 62.7% | Sep 2026 | Official leaderboard | |
| 3 | GPT-6.1 Sol | 61.7% | Sep 2026 | Official leaderboard | |
| 4 | GPT-5.6 Terra | 60.3% | Jul 2026 | Official leaderboard | |
| 5 | | 60% | Oct 2026 | Official leaderboard | |
| 6 | GPT-5.2 | 59.8% | Dec 2025 | Official leaderboard | |
| 7 | | 59.8% | Sep 2026 | Official leaderboard | |
| 8 | GPT-5.6 Luna | 59.2% | Jul 2026 | Official leaderboard | |
| 9 | Claude Opus 4.8 | 58.3% | May 2026 | Official leaderboard | |
| 10 | Claude Sonnet 5.5 | 58% | Sep 2026 | Official leaderboard | |
| 11 | o3 | 57.5% | Apr 2025 | Official leaderboard | |
| 12 | | 56.8% | Oct 2026 | Official leaderboard | |
| 13 | Claude Sonnet 5 | 56.7% | Jun 2026 | Official leaderboard | |
| 14 | | 55.2% | Sep 2026 | Official leaderboard | |
| 15 | Claude Opus 4.5 | 53.3% | Nov 2025 | Official leaderboard | |
| 16 | | 52.5% | Dec 2025 | Official leaderboard | |
| 17 | | 52.3% | Jun 2025 | Official leaderboard | |
| 18 | | 52.3% | Apr 2026 | Official leaderboard | |
| 19 | o4-mini | 52.2% | Apr 2025 | Official leaderboard | |
| 20 | Claude Opus 5.5 | 50.2% | Sep 2026 | Official leaderboard | |
| 21 | Claude Sonnet 4.5 | 49.8% | Sep 2025 | Official leaderboard | |
| 22 | Claude Opus 4.1 | 48.8% | Aug 2025 | Official leaderboard | |
| 23 | | 48.7% | May 2026 | Official leaderboard | |
| 24 | | 45.7% | Feb 2026 | Official leaderboard | |
| 25 | | 45.2% | Dec 2024 | Official leaderboard | |
| 26 | o3-mini | 45% | Jan 2025 | Official leaderboard | |
| 27 | | 44.5% | Mar 2025 | Official leaderboard | |
| 28 | | 43.3% | Nov 2025 | Official leaderboard | |
| 29 | Claude Fable 5 | 43.3% | Jun 2026 | Official leaderboard | |
| 30 | Claude Fable 5.1 | 42.8% | Sep 2026 | Official leaderboard | |
| 31 | | 40.2% | Apr 2025 | Official leaderboard | |
| 32 | | 23.7% | Jul 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The DualChem paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official DualChem 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 Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
10 of 11 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the benchmark’s paper (33 entries).
- Pass Models scored 32 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from October 2026, for Muse Spark Open.
- Pass Frontier models 6 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 67.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on scale.com: 32 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.