Benchmark Almanac

AI Engineering Lab simulation self-validation

GPT-4o Mar 2025 0.72 leads since April 2025
Not in model cards

Agents predict how a mechanical system should behave, inspect simulation outputs, and decide whether the model is correct. The authors score these decisions with F1.

The authors publish eight model comparisons on 140 simulation cases. Half of the cases contain deliberate parameter errors.

Released
April 2025
Kind
Apps and MCP servers
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Time series → Actions, Text
Interaction
Agentic
Environment
A simulator
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents, Robotics
Strongest model tested
Phi-4 #160 on the capability index
Last model added
March 2025
Scores refreshed
November 20th, 2026
8
Entries in its paper, 5 models we track

GPT-4o leads with 0.72 among models released by March 2025 GPT-4o leads with 0.72 among models released by March 2025

Best score per entry from the benchmark's paper, read on November 20th, 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 March 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 GPT-4o Mar 2025, Fails threshold 2 0.72
  2. 2 Llama3.3-70B-HF Fails threshold 1 0.71
  3. 3 QwenCoder-32B-Q4 Fails threshold 2 0.65
  4. 4 Phi-4 Fails threshold 1 0.62
  5. 5 Llama 3.1-70B Fails threshold 2 0.58
  6. 6 Qwen2.5-32B Fails threshold 1 0.55
  7. 7 FluentlyLM-Q4 Fails threshold 1 0.53
  8. 8 Qwen2.5-72B Fails threshold 1 0.53

Source: The AI Engineering Lab simulation self-validation paper

#EntryScoreSettingDateSource
1 GPT-4o Mar 2025 0.72 Fails threshold 2 Mar 2025 Official leaderboard
2 Llama3.3-70B-HF 0.71 Fails threshold 1 Official leaderboard
3 QwenCoder-32B-Q4 0.65 Fails threshold 2 Official leaderboard
4 Phi-4 0.62 Fails threshold 1 Dec 2024 Official leaderboard
5 Llama 3.1-70B 0.58 Fails threshold 2 Jul 2024 Official leaderboard
6 Qwen2.5-32B 0.55 Fails threshold 1 Sep 2024 Official leaderboard
7 FluentlyLM-Q4 0.53 Fails threshold 1 Official leaderboard
8 Qwen2.5-72B 0.53 Fails threshold 1 Sep 2024 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4o Mar 2025 0.72 Fails threshold 2 Mar 2025 Official leaderboard
2 Phi-4 0.62 Fails threshold 1 Dec 2024 Official leaderboard
3 Llama 3.1-70B 0.58 Fails threshold 2 Jul 2024 Official leaderboard
4 Qwen2.5-32B 0.55 Fails threshold 1 Sep 2024 Official leaderboard
5 Qwen2.5-72B 0.53 Fails threshold 1 Sep 2024 Official leaderboard

Number one over time

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

OpenAI
Benchmark paper Not tested since Apr 2025
GPT-4o 0.72

Source: The AI Engineering Lab simulation self-validation 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
0.55 0.60 0.65 0.70 0.75 2025 0.55 0.60 0.65 0.70 0.75 2025

Source: Official AI Engineering Lab simulation self-validation 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 Tool use

All 265 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Neon 56.3%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 20 months ago, in March 2025, for GPT-4o. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (8 entries).
  • Pass Models scored 5 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Phi-4 (#160).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 5 rows for models we track and 3 other entries 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.

How we check