reasoning benchmark
Agents' Last Exam Leaderboard
Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.
Updated Aug 17, 2026
Models10
Model coverage10
MetricScore
EvidenceB
Agents' Last Exam Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score52.7% | Percentile100.0% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score52.4% | Percentile88.9% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score50.4% | Percentile77.8% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score50.3% | Percentile66.7% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score42.9% | Percentile55.6% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score41.4% | Percentile44.4% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelZA | Score28.5% | Percentile33.3% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score26.3% | Percentile22.2% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelDE | Score25.7% | Percentile11.1% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelDE | Score25.2% | Percentile0.0% | Participants10 | EvidenceC | Evaluated |
Agents' Last Exam Highlights
The leading models and scores on this benchmark.
Agents' Last Exam Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Agents' Last Exam
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis agents' last exam AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01OPGPT-5.6 SolOpenAI
- Score
- 52.7%
- Price
- $5.0 input / $30 output per 1M tokens
- Speed
- Up to 27 tok/s via OpenAI
Strengths
- Ranks #1 of 10 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Agents' Last Exam, not total model capability
- 02ACQwen3.8 MaxAlibaba Cloud / Qwen Team
- Score
- 52.4%
- Price
- $2.0 input / $6.0 output per 1M tokens
Strengths
- Ranks #2 of 10 compared models
- 89th percentile on this benchmark
- C evidence result
Considerations
- This result measures Agents' Last Exam, not total model capability
- 03OPGPT-5.6 TerraOpenAI
- Score
- 50.4%
- Price
- $2.0 input / $12 output per 1M tokens
- Speed
- Up to 35 tok/s via OpenAI
Strengths
- Ranks #3 of 10 compared models
- 78th percentile on this benchmark
- C evidence result
Considerations
- This result measures Agents' Last Exam, not total model capability
- 04OPGPT-5.6 LunaOpenAI
- Score
- 50.3%
- Price
- $0.20 input / $1.2 output per 1M tokens
- Speed
- Up to 49 tok/s via OpenAI
Strengths
- Ranks #4 of 10 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures Agents' Last Exam, not total model capability
- 05ACQwen3.8-27BAlibaba Cloud / Qwen Team
- Score
- 42.9%
Strengths
- Ranks #5 of 10 compared models
- 56th percentile on this benchmark
- C evidence result
Considerations
- This result measures Agents' Last Exam, not total model capability
Selection summary
Best AI Models for Agents' Last Exam
GPT-5.6 Sol currently leads Agents' Last Exam with 52.7%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Agents' Last Exam?
What Agents' Last Exam measures and how its scores work.
Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Agents' Last Exam
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- agents-last-exam|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Agents' Last Exam.
Which model scores highest on Agents' Last Exam?
GPT-5.6 Sol is currently ranked first with 52.7%.
What does Agents' Last Exam measure?
Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.