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 2numericalverification

MMLU Pro

Robust multi-task language understanding reasoning benchmark with reasoning-focused questions.

12,000 tasks
21 models evaluated
Updated 2026
91.6%
Top Score
Top model
Claude Opus 5

Model Rankings

financebenchmark.ai · MMLU Pro
Anthropic logo
Anthropic logo
OpenAI logo
DeepSeek logo
xAI logo
Moonshot AI 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
88.0%
🥇Anthropic logoAnthropicClaude Opus 591.6%
🥈Anthropic logoAnthropicClaude Sonnet 587.5%
🥉OpenAI logoOpenAIGPT-5.6 Sol89.1%
4DeepSeek logoDeepSeekDeepSeek V4 FlashOPEN86.2%
5xAI logoxAIGrok 4.689.4%
6Moonshot AI logoMoonshot AIKimi K3OPEN88.0%
7Anthropic logoAnthropicClaude Fable 591.5%
8DeepSeek logoDeepSeekDeepSeek V4 Pro (0813)OPEN87.0%
9Google logoGoogleGemini 3.5 Flash Lite85.8%
10Google logoGoogleGemini 3.6 Flash88.5%
11Zhipu AI logoZhipu AIGLM 5.2OPEN86.7%
12OpenAI logoOpenAIGPT-5.6 Luna86.0%
13OpenAI logoOpenAIGPT-5.6 Terra86.7%
14xAI logoxAIGrok 4.589.2%
15Thinking Machines logoThinking MachinesInklingOPEN86.3%
16Thinking Machines logoThinking MachinesInkling SmallOPEN85.6%
17Ant Group logoAnt GroupLing 3.0 FlashOPEN82.0%
18Meta logoMetaMuse Spark 1.188.7%
19Meta logoMetaMuse Spark 1.288.3%
20NVIDIA logoNVIDIANemotron 3 UltraOPEN85.8%
21Alibaba logoAlibabaQwen 3.8 MaxOPEN88.6%
Full Results Table
#ModelOverallSourceDate
🥇
Anthropic logoClaude Opus 5
Anthropic
91.6arXiv:2406.015742026-07
🥈
Anthropic logoClaude Fable 5
Anthropic
91.5arXiv:2406.015742026-06
🥉
xAI logoGrok 4.6
xAI
89.4arXiv:2406.015742026-08
4
xAI logoGrok 4.5
xAI
89.2arXiv:2406.015742026-07
5
OpenAI logoGPT-5.6 Sol
OpenAI
89.1arXiv:2406.015742026-07
6
Meta logoMuse Spark 1.1
Meta
88.7arXiv:2406.015742026-07
7
Alibaba logoQwen 3.8 MaxOPEN
Alibaba
88.6arXiv:2406.015742026-08
8
Google logoGemini 3.6 Flash
Google
88.5arXiv:2406.015742026-07
9
Meta logoMuse Spark 1.2
Meta
88.3arXiv:2406.015742026-08
10
Moonshot AI logoKimi K3OPEN
Moonshot AI
88.0arXiv:2406.015742026-07
11
Anthropic logoClaude Sonnet 5
Anthropic
87.5arXiv:2406.015742026-06
12
DeepSeek logoDeepSeek V4 Pro (0813)OPEN
DeepSeek
87.0arXiv:2406.015742026-08
13
Zhipu AI logoGLM 5.2OPEN
Zhipu AI
86.7arXiv:2406.015742026-06
14
OpenAI logoGPT-5.6 Terra
OpenAI
86.7arXiv:2406.015742026-07
15
Thinking Machines logoInklingOPEN
Thinking Machines
86.3arXiv:2406.015742026-07
16
DeepSeek logoDeepSeek V4 FlashOPEN
DeepSeek
86.2arXiv:2406.015742026-07
17
OpenAI logoGPT-5.6 Luna
OpenAI
86.0arXiv:2406.015742026-07
18
Google logoGemini 3.5 Flash Lite
Google
85.8arXiv:2406.015742026-07
19
NVIDIA logoNemotron 3 UltraOPEN
NVIDIA
85.8arXiv:2406.015742026-06
20
Thinking Machines logoInkling SmallOPEN
Thinking Machines
85.6arXiv:2406.015742026-07
21
Ant Group logoLing 3.0 FlashOPEN
Ant Group
82.0arXiv:2406.015742026-07