Benchmark Almanac

FoamBench

Sonnet 3.5 29.3% tops its leaderboard o3-mini 22.5% leads the models we track
Not in model cards
Version 1

Agents create OpenFOAM cases from written specifications. The grader checks whether the solver finishes and whether the final flow field matches a reference simulation.

The authors publish six original model scores per split. An independent paper ran coding agents on the 16 Advanced cases.

Released
May 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, Code → Actions, Code
Interaction
Agentic
Environment
Terminal, OpenFOAM
Items from
Generated
Run by
Anyone
In views
Agents, Robotics
Strongest model tested
Gemini 2.5 Flash Sep 2025 #112 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 3 models we track

Sonnet 3.5 tops the leaderboard with 29.3% o3-mini leads with 22.5% among models released by September 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. The best model we track is o3-mini, at 22.5%. This view shows only models we track, each at its best.

The newest model with a score here came out in September 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 Sonnet 3.5 29.3%
  2. 2 GPT-4o (snapshot unspecified) 26.6%
  3. 3 o3-mini 22.5%
  4. 4 Claude 3.5 Haiku 18.9%
  5. 5 Gemini 2.5 Flash Sep 2025 6.80%
  6. 6 Gemma-2-9B-IT 0%

Source: Official FoamBench leaderboard

Source: Official FoamBench leaderboard

#EntryScoreSettingDateSource
1 Sonnet 3.5 29.3% Foam-Agent 1.0 Official leaderboard
2 GPT-4o (snapshot unspecified) 26.6% Foam-Agent 1.0 Official leaderboard
3 o3-mini 22.5% Foam-Agent 1.0 Jan 2025 Official leaderboard
4 Claude 3.5 Haiku 18.9% Foam-Agent 1.0 Oct 2024 Official leaderboard
5 Gemini 2.5 Flash Sep 2025 6.80% Foam-Agent 1.0 Sep 2025 Official leaderboard
6 Gemma-2-9B-IT 0% Foam-Agent 1.0 Official leaderboard
#ModelScoreSettingDateSource
1 o3-mini 22.5% Foam-Agent 1.0 Jan 2025 Official leaderboard
2 Claude 3.5 Haiku 18.9% Foam-Agent 1.0 Oct 2024 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 6.80% Foam-Agent 1.0 Sep 2025 Official leaderboard

Rankings by part

We read 2 parts from the benchmark’s own leaderboard: FoamBench Basic and FoamBench Advanced. Each ranks models on one part of the test. o3-mini leads FoamBench Basic and Claude 3.5 Haiku leads FoamBench Advanced. Arrows show how far a model moved from its overall rank among the models we track.

FoamBench Basic

3 models we track have a score here.

  1. 1 o3-mini 26.3%
  2. 2 Claude 3.5 Haiku 19.1%
  3. 3 Gemini 2.5 Flash Sep 2025 13.6%

Number one over time

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

OpenAI
Own leaderboard Not tested since Sep 2025
o3-mini 22.5%

Source: Official FoamBench leaderboard

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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3-mini Claude 3.5 Haiku 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3-mini

Source: Official FoamBench 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.

OpenAI Google DeepMind
FoamBench V2 Passed 85% in Oct 2026, by Gemini 3.1 Pro
FoamBench Not tested since Sep 2025
o3-mini 22.5%
FoamBench V2 Passed 85% in Oct 2026, by Gemini 3.1 Pro

Source: Official leaderboards

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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 3 models we track, plus 3 other entries on its leaderboard.
  • Note Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. That’s expected for a test replaced by FoamBench V2.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 2.5 Flash (#112).
  • Pass Headroom The best is 22.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on nithinsomu.github.io: 3 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