LevelBench-100 v4.1
Version 4.1
Models take over the books of small businesses using QuickBooks exports. They reconcile balances, identify missing evidence, and prepare closing entries across 12 workflows.
Level publishes 100 binary checks and 38 configurations. The 27 unassisted rows cover 22 distinct models after combining reasoning settings.
- Made by
- Level
- Released
- October 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- Browser
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- A version of another benchmark
- Occupations
- Management, Business and financial operations
- In views
- Agents, Law and finance
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3 tops the leaderboard with 100% GPT-6.1 Sol leads with 81% Gemini 4 Argon leads with 71% in a standard harness
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is GPT-6.1 Sol, at 81%. Agents built around a model, such as Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best. This view keeps only runs in a standard harness, a harness no model’s maker built. A maker’s own agent, such as Claude Code with a Claude model, is left out.
- 100.0 Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3
- 100.0 Level Playbooks (2,200+ Past Experiences) + GPT-5.6 Terra
- 100.0 Level Playbooks (2,200+ Past Experiences) + Gemini 3.8 Flash
- 100.0 Level Playbooks (2,200+ Past Experiences) + Claude Opus 5.5
- 100.0 Level Playbooks (2,200+ Past Experiences) + GPT-6.1 Sol
- 100.0 Level Playbooks (2,200+ Past Experiences) + Gemini 4 Argon
- 100.0 Level Playbooks (2,200+ Past Experiences) + Claude Haiku 5.5
- 84.0 Gemini CLI 0.64.0 + Gemini 4 Argon
- 83.0 Antigravity CLI 1.4.0 + Gemini 4 Argon
- 81.0 GPT-6.1 Sol
- 76.0 GPT-5.6 Terra
- 71.0
Gemini 4 Argon
- 69.0 Claude Opus 5.5
- 68.0 Claude Fable 5.1
- 64.0 Claude Sonnet 5.5
- 60.0 GPT-6 Astra
- 58.0
Gemini 3.8 Flash
- 55.0 Claude Haiku 5.5
- 54.0 Claude Opus 4.7
- 53.0 GPT-5.6 Sol
- 52.0
Gemini 3.1 Pro
- 50.0 Grok 4.5
- 49.0 GPT-6 Luna
- 48.0
Gemini 3.5 Flash
- 46.0
DeepSeek-V3
- 43.0 Grok 4.3
- 41.0 Kimi K2.5
- 39.0 Kimi K2
- 38.0 Claude Haiku 4.5
- 35.0
Qwen3-Next-80B-A3B
- 31.0
Qwen2.5-72B
- 1 Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3 Mar 2025 100%
- 2 Level Playbooks (2,200+ Past Experiences) + GPT-5.6 Terra 100%
- 3 Level Playbooks (2,200+ Past Experiences) + Gemini 3.8 Flash 100%
- 4 Level Playbooks (2,200+ Past Experiences) + Claude Opus 5.5 100%
- 5 Level Playbooks (2,200+ Past Experiences) + GPT-6.1 Sol 100%
- 6 Level Playbooks (2,200+ Past Experiences) + Gemini 4 Argon 100%
- 7 Level Playbooks (2,200+ Past Experiences) + Claude Haiku 5.5 100%
- 8 Gemini CLI 0.64.0 + Gemini 4 Argon Medium 84%
- 9 Antigravity CLI 1.4.0 + Gemini 4 Argon Medium 83%
- 10 GPT-6.1 Sol 81%
- 11 GPT-5.6 Terra 76%
- 12
Gemini 4 Argon Medium Thinking 71%
- 13 Claude Opus 5.5 69%
- 14 Claude Fable 5.1 68%
- 15 Claude Sonnet 5.5 64%
- 16 GPT-6 Astra Medium Effort 60%
- 17
Gemini 3.8 Flash 58%
- 18 Claude Haiku 5.5 55%
- 19 Claude Opus 4.7 54%
- 20 GPT-5.6 Sol 53%
- 21
Gemini 3.1 Pro 52%
- 22 Grok 4.5 50%
- 23 GPT-6 Luna Medium Effort 49%
- 24
Gemini 3.5 Flash 48%
- 25
DeepSeek-V3 Mar 2025 46%
- 26 Grok 4.3 43%
- 27 Kimi K2.5 41%
- 28 Kimi K2 Jul 2025 39%
- 29 Claude Haiku 4.5 38%
- 30
Qwen3-Next-80B-A3B 35%
- 31
Qwen2.5-72B 31%
Source: Official LevelBench-100 v4.1 leaderboard
- 81.0 GPT-6.1 Sol
- 76.0 GPT-5.6 Terra
- 71.0
Gemini 4 Argon
- 69.0 Claude Opus 5.5
- 68.0 Claude Fable 5.1
- 64.0 Claude Sonnet 5.5
- 60.0 GPT-6 Astra
- 58.0
Gemini 3.8 Flash
- 55.0 Claude Haiku 5.5
- 54.0 Claude Opus 4.7
- 53.0 GPT-5.6 Sol
- 52.0
Gemini 3.1 Pro
- 50.0 Grok 4.5
- 49.0 GPT-6 Luna
- 48.0
Gemini 3.5 Flash
- 46.0
DeepSeek-V3
- 43.0 Grok 4.3
- 41.0 Kimi K2.5
- 39.0 Kimi K2
- 38.0 Claude Haiku 4.5
- 35.0
Qwen3-Next-80B-A3B
- 31.0
Qwen2.5-72B
- 1 GPT-6.1 Sol 81%
- 2 GPT-5.6 Terra 76%
- 3
Gemini 4 Argon Medium Thinking 71%
- 4 Claude Opus 5.5 69%
- 5 Claude Fable 5.1 68%
- 6 Claude Sonnet 5.5 64%
- 7 GPT-6 Astra Medium Effort 60%
- 8
Gemini 3.8 Flash 58%
- 9 Claude Haiku 5.5 55%
- 10 Claude Opus 4.7 54%
- 11 GPT-5.6 Sol 53%
- 12
Gemini 3.1 Pro 52%
- 13 Grok 4.5 50%
- 14 GPT-6 Luna Medium Effort 49%
- 15
Gemini 3.5 Flash 48%
- 16
DeepSeek-V3 Mar 2025 46%
- 17 Grok 4.3 43%
- 18 Kimi K2.5 41%
- 19 Kimi K2 Jul 2025 39%
- 20 Claude Haiku 4.5 38%
- 21
Qwen3-Next-80B-A3B 35%
- 22
Qwen2.5-72B 31%
Source: Official LevelBench-100 v4.1 leaderboard
- 71.0
Gemini 4 Argon
- 69.0 Claude Opus 5.5
- 68.0 Claude Fable 5.1
- 67.0 GPT-6.1 Sol
- 64.0 Claude Sonnet 5.5
- 60.0 GPT-6 Astra
- 58.0
Gemini 3.8 Flash
- 57.0 GPT-5.6 Terra
- 55.0 Claude Haiku 5.5
- 54.0 Claude Opus 4.7
- 53.0 GPT-5.6 Sol
- 52.0
Gemini 3.1 Pro
- 50.0 Grok 4.5
- 49.0 GPT-6 Luna
- 48.0
Gemini 3.5 Flash
- 46.0
DeepSeek-V3
- 43.0 Grok 4.3
- 41.0 Kimi K2.5
- 39.0 Kimi K2
- 38.0 Claude Haiku 4.5
- 35.0
Qwen3-Next-80B-A3B
- 31.0
Qwen2.5-72B
- 1
Gemini 4 Argon Medium Thinking 71%
- 2 Claude Opus 5.5 69%
- 3 Claude Fable 5.1 68%
- 4 GPT-6.1 Sol High Effort 67%
- 5 Claude Sonnet 5.5 64%
- 6 GPT-6 Astra Medium Effort 60%
- 7
Gemini 3.8 Flash 58%
- 8 GPT-5.6 Terra Low Effort 57%
- 9 Claude Haiku 5.5 55%
- 10 Claude Opus 4.7 54%
- 11 GPT-5.6 Sol 53%
- 12
Gemini 3.1 Pro 52%
- 13 Grok 4.5 50%
- 14 GPT-6 Luna Medium Effort 49%
- 15
Gemini 3.5 Flash 48%
- 16
DeepSeek-V3 Mar 2025 46%
- 17 Grok 4.3 43%
- 18 Kimi K2.5 41%
- 19 Kimi K2 Jul 2025 39%
- 20 Claude Haiku 4.5 38%
- 21
Qwen3-Next-80B-A3B 35%
- 22
Qwen2.5-72B 31%
Source: Official LevelBench-100 v4.1 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3 Mar 2025 | 100% | Mar 2025 | Official leaderboard | |
| 2 | Level Playbooks (2,200+ Past Experiences) + GPT-5.6 Terra | 100% | Jul 2026 | Official leaderboard | |
| 3 | Level Playbooks (2,200+ Past Experiences) + Gemini 3.8 Flash | 100% | Sep 2026 | Official leaderboard | |
| 4 | Level Playbooks (2,200+ Past Experiences) + Claude Opus 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 5 | Level Playbooks (2,200+ Past Experiences) + GPT-6.1 Sol | 100% | Sep 2026 | Official leaderboard | |
| 6 | Level Playbooks (2,200+ Past Experiences) + Gemini 4 Argon | 100% | Sep 2026 | Official leaderboard | |
| 7 | Level Playbooks (2,200+ Past Experiences) + Claude Haiku 5.5 | 100% | Oct 2026 | Official leaderboard | |
| 8 | Gemini CLI 0.64.0 + Gemini 4 Argon | 84% | Medium | Sep 2026 | Official leaderboard |
| 9 | Antigravity CLI 1.4.0 + Gemini 4 Argon | 83% | Medium | Sep 2026 | Official leaderboard |
| 10 | GPT-6.1 Sol | 81% | Codex CLI | Sep 2026 | Official leaderboard |
| 11 | GPT-5.6 Terra | 76% | Codex CLI | Jul 2026 | Official leaderboard |
| 12 | | 71% | Medium Thinking | Sep 2026 | Official leaderboard |
| 13 | Claude Opus 5.5 | 69% | Sep 2026 | Official leaderboard | |
| 14 | Claude Fable 5.1 | 68% | Sep 2026 | Official leaderboard | |
| 15 | Claude Sonnet 5.5 | 64% | Sep 2026 | Official leaderboard | |
| 16 | GPT-6 Astra | 60% | Medium Effort | Sep 2026 | Official leaderboard |
| 17 | | 58% | Sep 2026 | Official leaderboard | |
| 18 | Claude Haiku 5.5 | 55% | Oct 2026 | Official leaderboard | |
| 19 | Claude Opus 4.7 | 54% | Apr 2026 | Official leaderboard | |
| 20 | GPT-5.6 Sol | 53% | Jul 2026 | Official leaderboard | |
| 21 | | 52% | Feb 2026 | Official leaderboard | |
| 22 | Grok 4.5 | 50% | Jul 2026 | Official leaderboard | |
| 23 | GPT-6 Luna | 49% | Medium Effort | Sep 2026 | Official leaderboard |
| 24 | | 48% | May 2026 | Official leaderboard | |
| 25 | | 46% | Mar 2025 | Official leaderboard | |
| 26 | Grok 4.3 | 43% | Apr 2026 | Official leaderboard | |
| 27 | Kimi K2.5 | 41% | Jan 2026 | Official leaderboard | |
| 28 | Kimi K2 Jul 2025 | 39% | Jul 2025 | Official leaderboard | |
| 29 | Claude Haiku 4.5 | 38% | Oct 2025 | Official leaderboard | |
| 30 | | 35% | Sep 2025 | Official leaderboard | |
| 31 | | 31% | Sep 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 81% | Codex CLI | Sep 2026 | Official leaderboard |
| 2 | GPT-5.6 Terra | 76% | Codex CLI | Jul 2026 | Official leaderboard |
| 3 | | 71% | Medium Thinking | Sep 2026 | Official leaderboard |
| 4 | Claude Opus 5.5 | 69% | Sep 2026 | Official leaderboard | |
| 5 | Claude Fable 5.1 | 68% | Sep 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 64% | Sep 2026 | Official leaderboard | |
| 7 | GPT-6 Astra | 60% | Medium Effort | Sep 2026 | Official leaderboard |
| 8 | | 58% | Sep 2026 | Official leaderboard | |
| 9 | Claude Haiku 5.5 | 55% | Oct 2026 | Official leaderboard | |
| 10 | Claude Opus 4.7 | 54% | Apr 2026 | Official leaderboard | |
| 11 | GPT-5.6 Sol | 53% | Jul 2026 | Official leaderboard | |
| 12 | | 52% | Feb 2026 | Official leaderboard | |
| 13 | Grok 4.5 | 50% | Jul 2026 | Official leaderboard | |
| 14 | GPT-6 Luna | 49% | Medium Effort | Sep 2026 | Official leaderboard |
| 15 | | 48% | May 2026 | Official leaderboard | |
| 16 | | 46% | Mar 2025 | Official leaderboard | |
| 17 | Grok 4.3 | 43% | Apr 2026 | Official leaderboard | |
| 18 | Kimi K2.5 | 41% | Jan 2026 | Official leaderboard | |
| 19 | Kimi K2 Jul 2025 | 39% | Jul 2025 | Official leaderboard | |
| 20 | Claude Haiku 4.5 | 38% | Oct 2025 | Official leaderboard | |
| 21 | | 35% | Sep 2025 | Official leaderboard | |
| 22 | | 31% | Sep 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 71% | Medium Thinking | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 69% | Sep 2026 | Official leaderboard | |
| 3 | Claude Fable 5.1 | 68% | Sep 2026 | Official leaderboard | |
| 4 | GPT-6.1 Sol | 67% | High Effort | Sep 2026 | Official leaderboard |
| 5 | Claude Sonnet 5.5 | 64% | Sep 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 60% | Medium Effort | Sep 2026 | Official leaderboard |
| 7 | | 58% | Sep 2026 | Official leaderboard | |
| 8 | GPT-5.6 Terra | 57% | Low Effort | Jul 2026 | Official leaderboard |
| 9 | Claude Haiku 5.5 | 55% | Oct 2026 | Official leaderboard | |
| 10 | Claude Opus 4.7 | 54% | Apr 2026 | Official leaderboard | |
| 11 | GPT-5.6 Sol | 53% | Jul 2026 | Official leaderboard | |
| 12 | | 52% | Feb 2026 | Official leaderboard | |
| 13 | Grok 4.5 | 50% | Jul 2026 | Official leaderboard | |
| 14 | GPT-6 Luna | 49% | Medium Effort | Sep 2026 | Official leaderboard |
| 15 | | 48% | May 2026 | Official leaderboard | |
| 16 | | 46% | Mar 2025 | Official leaderboard | |
| 17 | Grok 4.3 | 43% | Apr 2026 | Official leaderboard | |
| 18 | Kimi K2.5 | 41% | Jan 2026 | Official leaderboard | |
| 19 | Kimi K2 Jul 2025 | 39% | Jul 2025 | Official leaderboard | |
| 20 | Claude Haiku 4.5 | 38% | Oct 2025 | Official leaderboard | |
| 21 | | 35% | Sep 2025 | Official leaderboard | |
| 22 | | 31% | Sep 2024 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Bookkeeping, Accrual close and CFO analysis. GPT-5.6 Terra leads 2 of them, and GPT-6.1 Sol leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Bookkeeping
22 models we track have a score here.
- 1 GPT-5.6 Terra ↑1 76.5%
- 2 Claude Opus 5.5 ↑2 76.5%
- 3 GPT-6.1 Sol ↓2 76.5%
- 4
Gemini 4 Argon ↓1 76.5%
- 5 Claude Fable 5.1 73.5%
- 6
Gemini 3.8 Flash ↑2 64.7%
- 7 GPT-6 Astra 64.7%
- 8 Claude Sonnet 5.5 ↓2 64.7%
- 9 Claude Haiku 5.5 61.8%
- 10 Claude Opus 4.7 58.8%
Accrual close
22 models we track have a score here.
- 1 GPT-6.1 Sol 76.5%
- 2 GPT-5.6 Terra 73.5%
- 3 Claude Fable 5.1 ↑2 73.5%
- 4 Claude Opus 5.5 73.5%
- 5
Gemini 4 Argon ↓2 73.5%
- 6 Claude Sonnet 5.5 70.6%
- 7 GPT-6 Astra 58.8%
- 8
Gemini 3.8 Flash 52.9%
- 9
Gemini 3.1 Pro ↑3 47.1%
- 10 Claude Opus 4.7 47.1%
CFO analysis
22 models we track have a score here.
- 1 GPT-6.1 Sol 100%
- 2 GPT-5.6 Terra 75%
- 3
DeepSeek-V3 Mar 2025 ↑13 56.2%
- 4
Gemini 3.1 Pro ↑8 56.2%
- 5 Claude Opus 4.7 ↑5 56.2%
- 6 Grok 4.3 ↑11 56.2%
- 7
Gemini 3.5 Flash ↑8 56.2%
- 8 Grok 4.5 ↑5 56.2%
- 9 GPT-5.6 Sol ↑2 56.2%
- 10 Claude Fable 5.1 ↓5 56.2%
Deliverables
22 models we track have a score here.
- 1 GPT-5.6 Terra ↑1 81.2%
- 2 GPT-6.1 Sol ↓1 81.2%
- 3
Gemini 4 Argon 68.8%
- 4
DeepSeek-V3 Mar 2025 ↑12 56.2%
- 5 Kimi K2 Jul 2025 ↑14 56.2%
- 6 Kimi K2.5 ↑12 56.2%
- 7
Gemini 3.1 Pro ↑5 56.2%
- 8 Claude Opus 4.7 ↑2 56.2%
- 9 Grok 4.3 ↑8 56.2%
- 10
Gemini 3.5 Flash ↑5 56.2%
The best score, 100%, costs $0.008 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 LevelBench-100 v4.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Level Playbooks (2,200+ Past Experiences) + DeepSeek-V3 | Level Playbooks (2,200+ Past Experiences) | 100% | $0.008 | ||
| Level Playbooks (2,200+ Past Experiences) + GPT-5.6 Terra | Level Playbooks (2,200+ Past Experiences) | 100% | $0.03 | ||
| Level Playbooks (2,200+ Past Experiences) + Gemini 3.8 Flash | Level Playbooks (2,200+ Past Experiences) | 100% | $0.01 | ||
| Level Playbooks (2,200+ Past Experiences) + Claude Opus 5.5 | Level Playbooks (2,200+ Past Experiences) | 100% | $0.09 | ||
| Level Playbooks (2,200+ Past Experiences) + GPT-6.1 Sol | Level Playbooks (2,200+ Past Experiences) | 100% | $0.06 | ||
| Level Playbooks (2,200+ Past Experiences) + Gemini 4 Argon | Level Playbooks (2,200+ Past Experiences) | 100% | $0.04 | ||
| Level Playbooks (2,200+ Past Experiences) + Claude Haiku 5.5 | Level Playbooks (2,200+ Past Experiences) | 100% | $0.02 | ||
| Gemini CLI 0.64.0 + Gemini 4 Argon | Medium | Gemini CLI 0.64.0 | 84% | $0.05 | |
| Antigravity CLI 1.4.0 + Gemini 4 Argon | Medium | Antigravity CLI 1.4.0 | 83% | $0.05 | |
| GPT-6.1 Sol | Codex CLI | 81% | $0.14 | ||
| GPT-5.6 Terra | Codex CLI | 76% | $0.04 | ||
| Medium Thinking | 71% | $0.04 | |||
| Claude Opus 5.5 | 69% | $0.24 | |||
| Claude Fable 5.1 | 68% | $0.28 | |||
| GPT-6.1 Sol | High Effort | 67% | $0.26 | ||
| GPT-6.1 Sol | Medium Effort | 66% | $0.12 | ||
| High Thinking | 65% | $0.16 | |||
| Claude Sonnet 5.5 | 64% | $0.08 | |||
| Low Thinking | 63% | $0.03 | |||
| GPT-6.1 Sol | Low Effort | 62% | $0.08 | ||
| GPT-6 Astra | Medium Effort | 60% | $0.07 | ||
| 58% | $0.01 | ||||
| GPT-5.6 Terra | Low Effort | 57% | $0.03 | ||
| GPT-5.6 Terra | Medium Effort | 56% | $0.04 | ||
| Claude Haiku 5.5 | 55% | $0.02 | |||
| Claude Opus 4.7 | 54% | $0.22 | |||
| GPT-5.6 Sol | 53% | $0.10 | |||
| 52% | $0.06 | ||||
| Grok 4.5 | 50% | $0.09 | |||
| GPT-6 Luna | Medium Effort | 49% | $0.03 | ||
| 48% | $0.01 | ||||
| 46% | $0.008 | ||||
| Grok 4.3 | 43% | $0.03 | |||
| Kimi K2.5 | 41% | $0.01 | |||
| Kimi K2 Jul 2025 | 39% | $0.01 | |||
| Claude Haiku 4.5 | 38% | $0.02 | |||
| 35% | $0.01 | ||||
| 31% | $0.01 |
The best score, 81%, costs $0.14 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-5.6 Terra comes within 5 points of the best for $0.04 a task, 4 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official LevelBench-100 v4.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6.1 Sol | Codex CLI | 81% | $0.14 | ||
| GPT-5.6 Terra | Codex CLI | 76% | $0.04 | ||
| Medium Thinking | 71% | $0.04 | |||
| Claude Opus 5.5 | 69% | $0.24 | |||
| Claude Fable 5.1 | 68% | $0.28 | |||
| GPT-6.1 Sol | High Effort | 67% | $0.26 | ||
| GPT-6.1 Sol | Medium Effort | 66% | $0.12 | ||
| High Thinking | 65% | $0.16 | |||
| Claude Sonnet 5.5 | 64% | $0.08 | |||
| Low Thinking | 63% | $0.03 | |||
| GPT-6.1 Sol | Low Effort | 62% | $0.08 | ||
| GPT-6 Astra | Medium Effort | 60% | $0.07 | ||
| 58% | $0.01 | ||||
| GPT-5.6 Terra | Low Effort | 57% | $0.03 | ||
| GPT-5.6 Terra | Medium Effort | 56% | $0.04 | ||
| Claude Haiku 5.5 | 55% | $0.02 | |||
| Claude Opus 4.7 | 54% | $0.22 | |||
| GPT-5.6 Sol | 53% | $0.10 | |||
| 52% | $0.06 | ||||
| Grok 4.5 | 50% | $0.09 | |||
| GPT-6 Luna | Medium Effort | 49% | $0.03 | ||
| 48% | $0.01 | ||||
| 46% | $0.008 | ||||
| Grok 4.3 | 43% | $0.03 | |||
| Kimi K2.5 | 41% | $0.01 | |||
| Kimi K2 Jul 2025 | 39% | $0.01 | |||
| Claude Haiku 4.5 | 38% | $0.02 | |||
| 35% | $0.01 | ||||
| 31% | $0.01 |
The best score, 71%, costs $0.04 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 LevelBench-100 v4.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Medium Thinking | 71% | $0.04 | |||
| Claude Opus 5.5 | 69% | $0.24 | |||
| Claude Fable 5.1 | 68% | $0.28 | |||
| GPT-6.1 Sol | High Effort | 67% | $0.26 | ||
| GPT-6.1 Sol | Medium Effort | 66% | $0.12 | ||
| High Thinking | 65% | $0.16 | |||
| Claude Sonnet 5.5 | 64% | $0.08 | |||
| Low Thinking | 63% | $0.03 | |||
| GPT-6.1 Sol | Low Effort | 62% | $0.08 | ||
| GPT-6 Astra | Medium Effort | 60% | $0.07 | ||
| 58% | $0.01 | ||||
| GPT-5.6 Terra | Low Effort | 57% | $0.03 | ||
| GPT-5.6 Terra | Medium Effort | 56% | $0.04 | ||
| Claude Haiku 5.5 | 55% | $0.02 | |||
| Claude Opus 4.7 | 54% | $0.22 | |||
| GPT-5.6 Sol | 53% | $0.10 | |||
| 52% | $0.06 | ||||
| Grok 4.5 | 50% | $0.09 | |||
| GPT-6 Luna | Medium Effort | 49% | $0.03 | ||
| 48% | $0.01 | ||||
| 46% | $0.008 | ||||
| Grok 4.3 | 43% | $0.03 | |||
| Kimi K2.5 | 41% | $0.01 | |||
| Kimi K2 Jul 2025 | 39% | $0.01 | |||
| Claude Haiku 4.5 | 38% | $0.02 | |||
| 35% | $0.01 | ||||
| 31% | $0.01 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LevelBench-100 v4.1 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 LevelBench-100 v4.1 leaderboard
Source: Official LevelBench-100 v4.1 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.
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (31 entries).
- Pass Models scored 22 models we track, plus 9 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Pass Frontier models 6 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 81%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 38 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.