Benchmarks for what frontier AI hasn't solved
Digital Work Index
An economically weighted measure of model performance across eight challenging benchmarks covering software engineering, logical reasoning and writing, and professional environments.
23.62
Fable 5.1
23.61
Opus 5.5
23.03
GPT-6 Astra
21.75
Opus 5
21.19
GPT-6.1 Sol
20.52
Grok 4.6
19.3
Grok 4.7
16.92
Gemini Flash 3.8
16.76
Kimi K3
16.45
GLM 5.3
16.29
Muse Spark 1.3
11.81
Qwen 3.8 Max
11.07
DeepSeek V4 Pro
6.95
Nemotron 3 Ultra 550B
All Models
OpenAI
Sep 29, 2026
GPT-6.1 Sol
RANK BY BENCHMARK
Agentic Coding 2.0
42.8%
#2/14
SnorkelFinance 2.0
6.6%
#12/14
SnorkelLegal
20.7%
#14/14
SnorkelManufacturing
19.6%
#1/14
SnorkelRevOps
12.1%
#7/14
Anthropic
Sep 22, 2026
Opus 5.5
RANK BY BENCHMARK
Agentic Coding 2.0
40.4%
#3/14
Agents’ Last Exam
38.2%
#1/43
SnorkelFinance 2.0
18.6%
#5/14
SnorkelLegal
31.4%
#7/14
SnorkelManufacturing
10.4%
#7/14
xAI
Sep 21, 2026
Grok 4.7
RANK BY BENCHMARK
Agentic Coding 2.0
31.9%
#8/14
Senior SWE-Bench
27.4%
#8/19
SnorkelFinance 2.0
20.2%
#3/14
SnorkelLegal
32.8%
#6/14
SnorkelManufacturing
12.1%
#3/14
OpenAI
Sep 03, 2026
GPT-6 Astra
RANK BY BENCHMARK
Agentic Coding 2.0
47.6%
#1/14
Agents’ Last Exam
34.2%
#2/43
SnorkelFinance 2.0
11.6%
#9/14
SnorkelLegal
20.9%
#13/14
SnorkelManufacturing
10%
#9/14
All benchmarks
All Benchmarks
Sort: Newest
Benchmark Type: All
Enterprise Environments
Open Benchmarks Grants
MBABench 2.0
Evaluates agents on building financial models in spreadsheets, across 101 expert-written tasks.
By pass rate
1
Astra (Codex)
15.8%
2
Fable 5.1 (Claude Code)
7.9%
3
Astra (ChatGPT)
7.9%
Enterprise Environments
Proprietary
SnorkelManufacturing
Evaluates manufacturing decisions using fragmented plant-floor, engineering, and supplier evidence.
By pass@1
1
GPT-6.1 Sol
19.6%
2
Grok 4.6
16.4%
3
Grok 4.7
12.1%
Enterprise Environments
Proprietary
SnorkelRevOps
Evaluates revenue-operations workflows involving systems, controls, and business-state updates.
By pass@1
1
Grok 4.6
15.8%
2
Fable 5.1
14.0%
3
Kimi K3
13.1%
Enterprise Environments
Proprietary
SnorkelFinance 2.0
Evaluates financial workflows requiring evidence gathering, analysis, and compliance.
By pass@1
1
Grok 4.6
25.1%
2
GLM 5.3
21.2%
3
Grok 4.7
20.2%
Enterprise Environments
Proprietary
SnorkelUnderwrite 2.0
Evaluates auditable insurance underwriting decisions using incomplete, distributed evidence.
By pass@1
1
Grok 4.7
30.5%
2
GLM 5.3
30.4%
3
Nemotron 3 Ultra 550B
30.0%
Enterprise Environments
Proprietary
SnorkelLegal
Evaluates legal workflows requiring evidence, procedure, authority, and action.
By pass@1
1
Grok 4.6
40.7%
2
GLM 5.3
37.8%
3
Muse Spark 1.3
36.5%
View archived benchmarks
