Benchmark Almanac

ProOPF-B

Gemini 3 Pro 37.2% leads since February 2026
Not in model cards

Models translate operational requirements into executable optimal power flow programs. They change grid parameters, objectives, and constraints. The evaluator checks implementations against expert references.

Grid Studio scored 19 of 121 test cases and restored omitted specifications from six source records. ProOPF-D is the training dataset.

Released
February 2026
Kind
Scientific code
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Code
Interaction
Single turn
Environment
Code sandbox
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
December 2025
Scores refreshed
November 20th, 2026
6
Models scored in its paper

Gemini 3 Pro leads with 37.2% among models released by December 2025

Best score per model 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. Every run is in the next chart.

The newest model with a score here came out in December 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 Few-shot 37.2%
  2. 2 Qwen3-30B-A3B SFT (ProOPF-D), few-shot 35.5%
  3. 3 Claude Sonnet 4.5 Few-shot 33.9%
  4. 4 DeepSeek-V3.2 Few-shot 29.8%
  5. 5 Qwen3-Coder-480B-A35B Few-shot 24%
  6. 6 GPT-5.2 Few-shot 14.1%

Source: The ProOPF-B paper

#ModelScoreSettingDateSource
1 Gemini 3 Pro 37.2% Few-shot Nov 2025 Official leaderboard
2 Qwen3-30B-A3B 35.5% SFT (ProOPF-D), few-shot Apr 2025 Official leaderboard
3 Claude Sonnet 4.5 33.9% Few-shot Sep 2025 Official leaderboard
4 DeepSeek-V3.2 29.8% Few-shot Dec 2025 Official leaderboard
5 Qwen3-Coder-480B-A35B 24% Few-shot Jul 2025 Official leaderboard
6 GPT-5.2 14.1% Few-shot Dec 2025 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as Level 1, Level 2 and Level 3. Qwen3-30B-A3B leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Level 1

6 models we track have a score here.

  1. 1 Gemini 3 Pro 94.4%
  2. 2 DeepSeek-V3.2 ↑2 94.4%
  3. 3 Qwen3-Coder-480B-A35B ↑2 80.6%
  4. 4 Claude Sonnet 4.5 ↓1 77.8%
  5. 5 Qwen3-30B-A3B ↓3 75%
  6. 6 GPT-5.2 33.3%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Gemini 3 Pro
Zero-shot Few-shot
37.2%
Qwen3-30B-A3B
Zero-shot Few-shot SFT (ProOPF… SFT (ProOPF…
35.5%
Claude Sonnet 4.5
Zero-shot Few-shot
33.9%
DeepSeek-V3.2
Zero-shot Few-shot
29.8%
Qwen3-Coder-480B-A35B
Zero-shot Few-shot
24%
GPT-5.2
Zero-shot Few-shot
14.1%

Source: The ProOPF-B paper

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 3 Pro Few-shot 37.2%
Qwen3-30B-A3B SFT (ProOPF-D), few-shot 35.5%
Claude Sonnet 4.5 Few-shot 33.9%
DeepSeek-V3.2 Few-shot 29.8%
Qwen3-30B-A3B SFT (ProOPF-D), zero-shot 27.3%
Gemini 3 Pro Zero-shot 26.5%
DeepSeek-V3.2 Zero-shot 26.4%
Qwen3-Coder-480B-A35B Few-shot 24%
Claude Sonnet 4.5 Zero-shot 22.8%
Qwen3-30B-A3B Few-shot 14.9%
GPT-5.2 Few-shot 14.1%
GPT-5.2 Zero-shot 10.4%
Qwen3-Coder-480B-A35B Zero-shot 5.46%
Qwen3-30B-A3B Zero-shot 0%

Number one over time

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

Google DeepMind
Benchmark paper Not tested since Feb 2026
Gemini 3 Pro 37.2%

Source: The ProOPF-B 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 Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3 Pro Qwen3-30B-A3B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3 Pro

Source: Official ProOPF-B 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for GPT-5.2. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (6 entries).
  • Pass Models scored 6 models we track.
  • Warning Newest score The newest came 11 months ago, in December 2025, for GPT-5.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
  • Pass Headroom The best is 37.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 14 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.

How we check