Skip to main content
BenchLM
Advertise

Benchmark profile

Artificial Analysis Briefcase (AA Briefcase)

An independently evaluated professional-work benchmark reported as Elo.

Data verified

Benchmark score on AA Briefcase — July 23, 2026

BenchLM mirrors the published score view for AA Briefcase. Claude Fable 5 leads the public snapshot at 1574 , followed by Kimi K3 (1543) and GPT-5.6 Sol (1501). BenchLM does not use these results to rank models overall.

1Closed

Claude Fable 5

Anthropic

claude-fable-5

1574
Overall 83.68Context 1M+
2Closed

Kimi K3

Moonshot AI

kimi-3

1543
Overall 80.96Context 1.05M
3Closed

GPT-5.6 Sol

OpenAI

gpt-5-6-sol

1501
Overall 81.96Context 1M
19 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (19 models)

Score
1
Claude Fable 5Anthropic · Closed
1574
2
Kimi K3Moonshot AI · Closed
1543
3
GPT-5.6 SolOpenAI · Closed
1501
4
Claude Sonnet 5Anthropic · Closed
1388
5
Claude Opus 4.8Anthropic · Closed
1347
6
Grok 4.5xAI · Closed
1323
7
GLM-5.2Z.AI · Open weight
1260
8
GPT-5.5OpenAI · Closed
1154
9
MiniMax M3MiniMax · Open weight
1110
10
Gemini 3.6 FlashGoogle · Closed
961
11
DeepSeek V4 Pro (Max)DeepSeek · Open weight
932
12
Qwen3.7 MaxAlibaba · Closed
908
13
MiMo-V2.5-ProXiaomi · Closed
873
14
Nemotron 3 UltraNVIDIA · Open weight
870
15
Muse Spark 1.1Meta · Closed
863
16
InklingThinking Machines Lab · Open weight
836
17
DeepSeek V4 Flash (Max)DeepSeek · Open weight
831
18
Gemini 3.5 Flash-LiteGoogle · Closed
634
19
Mistral Medium 3.5 128BMistral · Open weight
506

The published AA Briefcase snapshot places Claude Fable 5 first at 1574. The third row is 73 score units behind. The broader top-10 range is 613 score units, so the table still separates the published systems.

19 models have been evaluated on AA Briefcase. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AA Briefcase is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Briefcase

Year

2026

Tasks

Professional knowledge-work tasks

Format

Elo

Difficulty

Professional work

Stored as a display-only Elo rating.

Artificial Analysis Briefcase Benchmark Leaderboard

BenchLM freshness & provenance

Version

AA Briefcase 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does AA Briefcase measure?

An independently evaluated professional-work benchmark reported as Elo.

Which model scores highest on AA Briefcase?

Claude Fable 5 by Anthropic currently leads with a score of 1574 on AA Briefcase.

How many models are evaluated on AA Briefcase?

19 AI models have been evaluated on AA Briefcase on BenchLM.

Compare Top Models on AA Briefcase

Claude Fable 5 vs Kimi K3Kimi K3 vs GPT-5.6 SolGPT-5.6 Sol vs Claude Sonnet 5Claude Sonnet 5 vs Claude Opus 4.8
Last updated: July 23, 2026 · BenchLM version AA Briefcase 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.