Benchmark Almanac

FrontierRSI

Claude Opus 5.5 34.3% leads since November 2026
Not in model cards

Agents do 27 open-ended AI research and engineering tasks across pre-training, post-training and harnesses, inference serving and GPU kernels. Each trial is scored against the best valid result any model reached.

Each model runs two trials per task in an agent harness on H100s. A trial within 10% of the best valid result earns partial credit, and anything worse or failing a correctness check scores 0. The overall score is the mean over all tasks. The repo holds 8 of the 27 tasks.

Made by
Abundant AI
Released
November 2026
Kind
AI research tasks
Level
Research frontier
Scored
Checked automatically
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
Claude Fable 5.2 #2 on the capability index
Last model added
November 2026
Scores refreshed
November 18th, 2026
9
Models scored on its own leaderboard

Claude Opus 5.5 leads with 34.3%

Best score per model from the benchmark's own leaderboard, read on November 18th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

  1. 1 Claude Opus 5.5 max 34.3%
  2. 2 Claude Fable 5.2 max 33%
  3. 3 Gemini 4 Carbon high 29.8%
  4. 4 Gemini 4 Argon high 23.6%
  5. 5 GPT-6.1 Sol max 23.5%
  6. 6 GPT-6 Astra max 20.9%
  7. 7 Kimi K3.1 Pro max 13.6%
  8. 8 Muse Wonder max 12%
  9. 9 Grok 4.7 xhigh 8.92%

Source: Official FrontierRSI leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 34.3% max, Claude Code Sep 2026 Official leaderboard
2 Claude Fable 5.2 33% max, Claude Code Nov 2026 Official leaderboard
3 Gemini 4 Carbon 29.8% high, Antigravity CLI Oct 2026 Official leaderboard
4 Gemini 4 Argon 23.6% high, Antigravity CLI Sep 2026 Official leaderboard
5 GPT-6.1 Sol 23.5% max, Codex Sep 2026 Official leaderboard
6 GPT-6 Astra 20.9% max, Codex Sep 2026 Official leaderboard
7 Kimi K3.1 Pro 13.6% max, Claude Code Oct 2026 Official leaderboard
8 Muse Wonder 12% max, Muse Code Oct 2026 Official leaderboard
9 Grok 4.7 8.92% xhigh, Grok Build Sep 2026 Official leaderboard

Rankings by part

We read 31 parts from the benchmark’s own leaderboard in 2 groups: research area and task. Each ranks models on one part of the test. Claude Opus 5.5 leads 8 of them, and 6 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Pre-training

Optimizers, objectives, architectures and training of draft models, scored on held-out loss or latency. 9 models we track have a score here.

  1. 1 GPT-6.1 Sol ↑4 44.1%
  2. 2 Claude Opus 5.5 ↓1 44.1%
  3. 3 Claude Fable 5.2 ↓1 41.4%
  4. 4 Gemini 4 Carbon ↓1 26.9%
  5. 5 Gemini 4 Argon ↓1 26.8%
  6. 6 GPT-6 Astra 25.4%
  7. 7 Kimi K3.1 Pro 15.7%
  8. 8 Muse Wonder 14.6%
  9. 9 Grok 4.7 9.25%

The best score, 34.3%, costs $1,114 for the full run

Runs on the cost frontier score higher than any run that's cheaper. Gemini 4 Carbon at high comes within 4.5 points of the best for $386 for the full run, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Anthropic Meta Moonshot AI Google DeepMind Cost frontier One model at each effort level
0% 10% 20% 30% 40% $100 $200 $500 $1,000 $2,000 $5,000 $10,000 Cost of the full run, log scale Claude Opus 5.5, max Gemini 4 Carbon, high Kimi K3.1 Pro, max Muse Wonder, max 0% 10% 20% 30% 40% $100 $1,000 $10,000 Cost of the full run, log scale Claude Opus 5.5, max Gemini 4 Carbon, high

Source: Official FrontierRSI leaderboard

ModelEffortHarnessScoreCost of the full runOutput tokens
Claude Opus 5.5 max Claude Code 34.3% $1,114
Claude Fable 5.2 max Claude Code 33% $2,012
Gemini 4 Carbon high Antigravity CLI 29.8% $386
Gemini 4 Argon high Antigravity CLI 23.6% $398
GPT-6.1 Sol max Codex 23.5% $531
GPT-6 Astra max Codex 20.9% $2,829
Kimi K3.1 Pro max Claude Code 13.6% $265
Muse Wonder max Muse Code 12% $262
Grok 4.7 xhigh Grok Build 8.92% $1,645

Number one over time

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

Anthropic
Own leaderboard 1 leader

Source: Official FrontierRSI 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% 2027 Near the ceiling (85%) Claude Opus 5.5 GPT-6 Astra 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Claude Opus 5.5 GPT-6 Astra

Source: Official FrontierRSI 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 AI research

All 164 in AI research
  • PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics. Qwen 3.8 Max 93%
  • MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
  • PostTrainBench 1.2 In use CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain. Claude Fable 5.1 44.6%
  • MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6.2 Astra 96.1%
  • PMPP-Hard In use Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours. Kimi K3 0.71
  • KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup. MiniMax-M3 28.8%

Data audit

All 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (9 entries).
  • Pass Models scored 9 models we track.
  • Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
  • Pass Frontier models 6 of the top 10 have a score, led by Claude Fable 5.2 (#2).
  • Pass Headroom The best is 34.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on frontier-rsi.org: 9 rows for models we track at the last read.
  • Pass Last read November 18th, 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