Benchmark Almanac

FEM-Bench

Gemini 3 Pro 87.9% leads since November 2025
Not in model cards

Models implement finite element functions and write tests for them. The evaluator checks numerical outputs and whether the tests distinguish reference functions from faulty implementations.

The authors compare ten models on 33 tasks from computational mechanics coursework. They publish separate results for function implementation and test generation.

Released
August 2025
Kind
Scientific code
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
In views
CAD
Strongest model tested
Gemini 3 Pro #56 on the capability index
Last model added
November 2025
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 9 models we track

Gemini 3 Pro leads with 87.9% among models released by November 2025 Gemini 3 Pro leads with 87.9% among models released by November 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. This view shows only models we track, each at its best.

The newest model with a score here came out in November 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 Gemini 3 Pro First run 87.9%
  2. 2 Claude Opus 4.5 First run 84.8%
  3. 3 Gemini 2.5 Pro Jun 2025, First run 78.8%
  4. 4 GPT-5 mini First run 75.8%
  5. 5 GPT-5 First run 66.7%
  6. 6 Qwen3-Coder-480B-A35B First run 63.6%
  7. 7 Claude Haiku 4.5 First run 57.6%
  8. 8 qwen3-next-80b First run 48.5%
  9. 9 Llama 4 Maverick First run 48.5%
  10. 10 Llama 4 Scout First run 18.2%

Source: Official FEM-Bench leaderboard

#EntryScoreSettingDateSource
1 Gemini 3 Pro 87.9% First run Nov 2025 Official leaderboard
2 Claude Opus 4.5 84.8% First run Nov 2025 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 78.8% First run Jun 2025 Official leaderboard
4 GPT-5 mini 75.8% First run Aug 2025 Official leaderboard
5 GPT-5 66.7% First run Aug 2025 Official leaderboard
6 Qwen3-Coder-480B-A35B 63.6% First run Jul 2025 Official leaderboard
7 Claude Haiku 4.5 57.6% First run Oct 2025 Official leaderboard
8 qwen3-next-80b 48.5% First run Official leaderboard
9 Llama 4 Maverick 48.5% First run Apr 2025 Official leaderboard
10 Llama 4 Scout 18.2% First run Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3 Pro 87.9% First run Nov 2025 Official leaderboard
2 Claude Opus 4.5 84.8% First run Nov 2025 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 78.8% First run Jun 2025 Official leaderboard
4 GPT-5 mini 75.8% First run Aug 2025 Official leaderboard
5 GPT-5 66.7% First run Aug 2025 Official leaderboard
6 Qwen3-Coder-480B-A35B 63.6% First run Jul 2025 Official leaderboard
7 Claude Haiku 4.5 57.6% First run Oct 2025 Official leaderboard
8 Llama 4 Maverick 48.5% First run Apr 2025 Official leaderboard
9 Llama 4 Scout 18.2% First run Apr 2025 Official leaderboard

Rankings by part

We read 66 parts from the benchmark’s own leaderboard in 2 groups: function correctness and joint test success. Each ranks models on one part of the test. Llama 4 Maverick leads 31 of them, and 7 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

linear_elastic_CC0_H0_T0

9 models we track have a score here.

  1. 1 Llama 4 Maverick ↑7 100%
  2. 2 Gemini 2.5 Pro Jun 2025 ↑1 100%
  3. 3 Qwen3-Coder-480B-A35B ↑3 100%
  4. 4 GPT-5 ↑1 100%
  5. 5 GPT-5 mini ↓1 100%
  6. 6 Gemini 3 Pro ↓5 100%
  7. 7 Claude Opus 4.5 ↓5 100%
  8. 8 Llama 4 Scout ↑1 0%
  9. 9 Claude Haiku 4.5 ↓2 0%

2 models have held number one on the official leaderboard since its release in August 2025

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

Google DeepMind
Own leaderboard Passed 85% in Nov 2025, by Gemini 3 Pro
Gemini 3 Pro 87.9%

Source: Official FEM-Bench leaderboard

Gemini 3 Pro on the official leaderboard passed 85% in November 2025

That was 3 months after its release. By the same age, 12% of the benchmarks from 2025 had passed 85%. 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 2026 Near the ceiling (85%) Gemini 3 Pro Gemini 2.5 Pro Llama 4 Maverick 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3 Pro Gemini 2.5 Pro

Source: Official FEM-Bench 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 Coding

All 523 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
  • Note Newest score The newest came 12 months ago, in November 2025, for Claude Opus 4.5. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3 Pro (#56).
  • Note Headroom Saturated. The best is 87.9%, past 85% since November 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 9 rows for models we track and 1 other entry 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