2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 • 2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 •
Tier 3documentQAforensic

Excel Modeling Benchmark

Evaluating agents on Excel-based financial modeling and spreadsheet valuation tasks (EMB v1.1).

Variable tasks
44 models evaluated
Updated 2026
76.7%
Top Score
Top model
Claude Fable 5.1

Model Rankings

financebenchmark.ai · EMB
Anthropic logo
OpenAI logo
Google logo
DeepSeek logo
xAI logo
Moonshot AI logo
MiniMax logo
Anthropic logo
Anthropic logo
OpenAI logo
Google logo
DeepSeek logo
xAI logo
Moonshot AI logo
MiniMax logo
Anthropic logo
DeepSeek logo
Google logo
Google logo
Zhipu AI logo
OpenAI logo
OpenAI logo
xAI logo
Thinking Machines logo
Thinking Machines logo
Ant Group logo
Meta logo
Meta logo
NVIDIA logo
Alibaba logo
Alibaba logo
OpenAI logo
Anthropic logo
Google logo
Meta logo
Meta logo
DeepSeek logo
Zhipu AI logo
Zhipu AI logo
Google logo
Anthropic logo
Anthropic logo
OpenAI logo
OpenAI logo
57.9%
🥇Anthropic logoAnthropicClaude Opus 4.763.7%
🥈OpenAI logoOpenAIGPT-5.564.5%
🥉Google logoGoogleGemini 3.1 Pro52.6%
4DeepSeek logoDeepSeekDeepSeek V4 ProOPEN51.6%
5xAI logoxAIGrok 4.318.4%
6Moonshot AI logoMoonshot AIKimi K2.6OPEN57.9%
7MiniMax logoMiniMaxMiniMax M2.7OPEN28.4%
8Anthropic logoAnthropicClaude Opus 573.6%
9Anthropic logoAnthropicClaude Sonnet 566.3%
10OpenAI logoOpenAIGPT-5.6 Sol72.3%
11Google logoGoogleGemini 3.7 Flash71.3%
12DeepSeek logoDeepSeekDeepSeek V4 FlashOPEN57.0%
13xAI logoxAIGrok 4.662.7%
14Moonshot AI logoMoonshot AIKimi K3OPEN71.3%
15MiniMax logoMiniMaxMiniMax M3OPEN47.8%
16Anthropic logoAnthropicClaude Fable 573.7%
17DeepSeek logoDeepSeekDeepSeek V4 Pro (0813)OPEN52.8%
18Google logoGoogleGemini 3.5 Flash Lite43.2%
19Google logoGoogleGemini 3.6 Flash65.4%
20Zhipu AI logoZhipu AIGLM 5.2OPEN61.5%
21OpenAI logoOpenAIGPT-5.6 Luna67.1%
22OpenAI logoOpenAIGPT-5.6 Terra66.2%
23xAI logoxAIGrok 4.552.9%
24Thinking Machines logoThinking MachinesInklingOPEN38.4%
25Thinking Machines logoThinking MachinesInkling SmallOPEN31.8%
26Ant Group logoAnt GroupLing 3.0 FlashOPEN25.0%
27Meta logoMetaMuse Spark 1.156.4%
28Meta logoMetaMuse Spark 1.257.0%
29NVIDIA logoNVIDIANemotron 3 UltraOPEN31.7%
30Alibaba logoAlibabaQwen 3.7 Plus49.4%
31Alibaba logoAlibabaQwen 3.8 MaxOPEN60.1%
32OpenAI logoOpenAIGPT-6 Astra72.7%
33Anthropic logoAnthropicClaude Fable 5.176.7%
34Google logoGoogleGemini 3.8 Flash72.9%
35Meta logoMetaMuse Spark 1.362.7%
36Meta logoMetaMuse Spark 1.3 Max67.4%
37DeepSeek logoDeepSeekDeepSeek V4.1 FlashOPEN69.2%
38Zhipu AI logoZhipu AIGLM 5.3OPEN69.1%
39Zhipu AI logoZhipu AIGLM 5.3 FlashOPEN55.9%
40Google logoGoogleGemini 4 Argon74.8%
41Anthropic logoAnthropicClaude Opus 5.575.8%
42Anthropic logoAnthropicClaude Sonnet 5.575.9%
43OpenAI logoOpenAIGPT-6 Sol71.1%
44OpenAI logoOpenAIGPT-6 Luna70.0%
Full Results Table
#ModelOverallSourceDate
🥇
Anthropic logoClaude Fable 5.1
Anthropic
76.7VALS (2026)2026-10
🥈
Anthropic logoClaude Sonnet 5.5
Anthropic
75.9VALS (2026)2026-10
🥉
Anthropic logoClaude Opus 5.5
Anthropic
75.8VALS (2026)2026-10
4
Google logoGemini 4 Argon
Google
74.8VALS (2026)2026-10
5
Anthropic logoClaude Fable 5
Anthropic
73.7VALS (2026)2026-09
6
Anthropic logoClaude Opus 5
Anthropic
73.6VALS (2026)2026-09
7
Google logoGemini 3.8 Flash
Google
72.9VALS (2026)2026-10
8
OpenAI logoGPT-6 Astra
OpenAI
72.7VALS (2026)2026-10
9
OpenAI logoGPT-5.6 Sol
OpenAI
72.3VALS (2026)2026-09
10
Google logoGemini 3.7 Flash
Google
71.3VALS (2026)2026-09
11
Moonshot AI logoKimi K3OPEN
Moonshot AI
71.3VALS (2026)2026-10
12
OpenAI logoGPT-6 Sol
OpenAI
71.1VALS (2026)2026-10
13
OpenAI logoGPT-6 Luna
OpenAI
70.0VALS (2026)2026-10
14
DeepSeek logoDeepSeek V4.1 FlashOPEN
DeepSeek
69.2VALS (2026)2026-10
15
Zhipu AI logoGLM 5.3OPEN
Zhipu AI
69.1VALS (2026)2026-10
16
Meta logoMuse Spark 1.3 Max
Meta
67.4VALS (2026)2026-09
17
OpenAI logoGPT-5.6 Luna
OpenAI
67.1VALS (2026)2026-09
18
Anthropic logoClaude Sonnet 5
Anthropic
66.3VALS (2026)2026-09
19
OpenAI logoGPT-5.6 Terra
OpenAI
66.2VALS (2026)2026-09
20
Google logoGemini 3.6 Flash
Google
65.4VALS (2026)2026-09
21
OpenAI logoGPT-5.5
OpenAI
64.5VALS (2026)2026-09
22
Anthropic logoClaude Opus 4.7
Anthropic
63.7VALS (2026)2026-09
23
xAI logoGrok 4.6
xAI
62.7VALS (2026)2026-09
24
Meta logoMuse Spark 1.3
Meta
62.7VALS (2026)2026-09
25
Zhipu AI logoGLM 5.2OPEN
Zhipu AI
61.5VALS (2026)2026-09
26
Alibaba logoQwen 3.8 MaxOPEN
Alibaba
60.1VALS (2026)2026-09
27
Moonshot AI logoKimi K2.6OPEN
Moonshot AI
57.9VALS (2026)2026-09
28
DeepSeek logoDeepSeek V4 FlashOPEN
DeepSeek
57.0VALS (2026)2026-09
29
Meta logoMuse Spark 1.2
Meta
57.0VALS (2026)2026-09
30
Meta logoMuse Spark 1.1
Meta
56.4VALS (2026)2026-09
31
Zhipu AI logoGLM 5.3 FlashOPEN
Zhipu AI
55.9VALS (2026)2026-09
32
xAI logoGrok 4.5
xAI
52.9VALS (2026)2026-09
33
DeepSeek logoDeepSeek V4 Pro (0813)OPEN
DeepSeek
52.8VALS (2026)2026-09
34
Google logoGemini 3.1 Pro
Google
52.6VALS (2026)2026-09
35
DeepSeek logoDeepSeek V4 ProOPEN
DeepSeek
51.6VALS (2026)2026-09
36
Alibaba logoQwen 3.7 Plus
Alibaba
49.4VALS (2026)2026-09
37
MiniMax logoMiniMax M3OPEN
MiniMax
47.8VALS (2026)2026-09
38
Google logoGemini 3.5 Flash Lite
Google
43.2VALS (2026)2026-09
39
Thinking Machines logoInklingOPEN
Thinking Machines
38.4VALS (2026)2026-09
40
Thinking Machines logoInkling SmallOPEN
Thinking Machines
31.8VALS (2026)2026-09
41
NVIDIA logoNemotron 3 UltraOPEN
NVIDIA
31.7VALS (2026)2026-09
42
MiniMax logoMiniMax M2.7OPEN
MiniMax
28.4VALS (2026)2026-09
43
Ant Group logoLing 3.0 FlashOPEN
Ant Group
25.0VALS (2026)2026-09
44
xAI logoGrok 4.3
xAI
18.4VALS (2026)2026-09