Benchmark Almanac

STAGE Cross-Scene Narrative Evolution Reasoning

Claude Sonnet 4.6 65.1% leads since May 2026
Not in model cards

Models answer questions that require evidence from different scenes in a movie. A judge compares the answer with a reference.

The STAGE team tested seven model backbones on 5,010 questions across 151 screenplays in its Narrative Knowledge Weaver paper.

Released
May 2026
Kind
Reasoning over long documents
Level
School
Scored
Graded by a model
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
9
Entries in its paper, 8 models we track

Claude Sonnet 4.6 leads with 65.1% among models released by April 2026 Claude Sonnet 4.6 leads with 65.1% among models released by April 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Table 3 lists Hybrid RAG first, so this is its average accuracy on the full Task II release. 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 April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Sonnet 4.6 65.1%
  2. 2 GPT-5.5 65%
  3. 3 Gemini 3.1 Pro 63.9%
  4. 4 Qwen3-235B 63.7%
  5. 5 Kimi K2.6 Full screenplay 62.7%
  6. 6 Llama 3.1-70B 55.8%
  7. 7 Qwen3-30B-A3B 55.3%
  8. 8 Qwen3-8B 46.1%
  9. 9 Llama 3.1-8B 41.5%

Source: The STAGE Cross-Scene Narrative Evolution Reasoning paper

#EntryScoreSettingDateSource
1 Claude Sonnet 4.6 65.1% Hybrid RAG Feb 2026 Official leaderboard
2 GPT-5.5 65% Hybrid RAG Apr 2026 Official leaderboard
3 Gemini 3.1 Pro 63.9% Hybrid RAG Feb 2026 Official leaderboard
4 Qwen3-235B 63.7% Hybrid RAG Official leaderboard
5 Kimi K2.6 62.7% Full screenplay Apr 2026 Official leaderboard
6 Llama 3.1-70B 55.8% Hybrid RAG Jul 2024 Official leaderboard
7 Qwen3-30B-A3B 55.3% Hybrid RAG Apr 2025 Official leaderboard
8 Qwen3-8B 46.1% Hybrid RAG Apr 2025 Official leaderboard
9 Llama 3.1-8B 41.5% LightRAG Jul 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Sonnet 4.6 65.1% Hybrid RAG Feb 2026 Official leaderboard
2 GPT-5.5 65% Hybrid RAG Apr 2026 Official leaderboard
3 Gemini 3.1 Pro 63.9% Hybrid RAG Feb 2026 Official leaderboard
4 Kimi K2.6 62.7% Full screenplay Apr 2026 Official leaderboard
5 Llama 3.1-70B 55.8% Hybrid RAG Jul 2024 Official leaderboard
6 Qwen3-30B-A3B 55.3% Hybrid RAG Apr 2025 Official leaderboard
7 Qwen3-8B 46.1% Hybrid RAG Apr 2025 Official leaderboard
8 Llama 3.1-8B 41.5% LightRAG Jul 2024 Official leaderboard

Number one over time

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

Anthropic
Benchmark paper Not tested since May 2026

Source: The STAGE Cross-Scene Narrative Evolution Reasoning 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%) Claude Sonnet 4.6 Llama 3.1-70B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Sonnet 4.6 Llama 3.1-70B

Source: Official STAGE Cross-Scene Narrative Evolution Reasoning 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 Long context

All 115 in Long context
  • MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens. Muse Spark 1.3 98.5%
  • LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy. Inkling 2 Small 70.6%
  • GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
  • OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin. Gemini 3.7 Flash 89%
  • CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
  • AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key. Step 5 Preview 88.3%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for GPT-5.5. 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 (9 entries).
  • Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 7 months ago, in April 2026, for GPT-5.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 65.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 36 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