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 •
Home/Models/Qwen 3.8 Max
Alibaba logoAlibaba

Qwen 3.8 Max

Open-weight#24 on FB Leaderboard1M contextReleased 2026-08-0325 benchmarks evaluated
View Benchmarks →Submit a score
62.2
FB Score
#24
Overall rank
FB Score62.2Rank #24
Best benchmark93.7%GPQA Diamond
PAVE overall—%Level 1-4
Benchmarks25 / 42Evaluated
✦Official Certification
Get your AI model certified by FinanceBenchmark
Verified performance scores · Embeddable trust badge · Leaderboard listing
Claim Your Badge

Score by domain

Verification
67.9%
Rank #19 of 33
Document QA
72.9%
Rank #14 of 45
Numerical
73.9%
Rank #18 of 32
Forensic
59.3%
Rank #19 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
50.1%
Rank #21 of 44
Performance profile
80%Verification67.9%Document QA72.9%Numerical73.9%Forensic59.3%Agent Tasks50.1%
Benchmark results25 evaluated · 17 pending
BenchmarkScoreRankTierWeightSourceDate
Pave Interchange Fee Benchmark
VerificationForensic
——Tier 130FB 2026Pending
FinanceBench
Document QA
——Tier 220FB 2026Pending
FinBen
Multi-domain
——Tier 310FB 2026Pending
FinQA
Numerical
——Tier 220FB 2026Pending
ConvFinQA
Document QA
——Tier 220FB 2026Pending
Finance Agent Benchmark
Agent Tasks
50.6#27 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
51.8#15 / 22Tier 125FB 20262026-08
MortgageTax Benchmark
NumericalForensic
64.0#19 / 22Tier 220FB 20262026-08
TaxEval v2
VerificationForensic
75.5#11 / 24Tier 220FB 20262026-08
Code Migration
Agent Tasks
24.0#16 / 23Tier 310FB 20262026-08
CyberBench
Forensic
——Tier 310FB 2026Pending
Excel Modeling Benchmark
Document QAForensic
60.1#26 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
47.6#5 / 22Tier 310FB 20262026-08
MedCode
Verification
40.7#17 / 20Tier 310FB 20262026-08
MedScribe
Document QA
85.0#10 / 20Tier 310FB 20262026-08
ProofBench v1.1
NumericalVerification
58.0#8 / 13Tier 310FB 20262026-08
SAGE
Agent Tasks
51.3#4 / 17Tier 310FB 20262026-08
Public Benefits Bench
VerificationForensic
67.1#5 / 16Tier 310FB 20262026-08
Vibe Code Bench v1.1
Agent Tasks
64.7#14 / 23Tier 310FB 20262026-08
Harvey's Legal Agent
Agent TasksForensic
10.4#7 / 22Tier 310FB 20262026-08
GPQA Diamond
NumericalVerification
93.7#3 / 20Tier 215FB 20262026-08
IOI
Numerical
73.0#3 / 8Tier 310FB 20262026-08
LiveCodeBench
Agent Tasks
87.8#5 / 19Tier 310FB 20262026-08
LegalBench
Document QAForensic
83.6#15 / 21Tier 310FB 20262026-08
MMLU Pro
NumericalVerification
88.6#7 / 21Tier 215FB 20262026-08
MMMU
Document QANumerical
88.0#5 / 14Tier 310FB 20262026-08
ProgramBench
Agent Tasks
0.0#8 / 17Tier 310FB 20262026-08
SkillsBench
Agent Tasks
42.0#14 / 17Tier 310FB 20262026-08
SWE-bench
Agent Tasks
85.3#11 / 22Tier 220FB 20262026-08
Terminal-Bench 2.1
Agent Tasks
67.2#13 / 23Tier 310FB 20262026-08
RSI Index
Agent TasksNumerical
——Tier 310FB 2026Pending
Time Horizon Index
ForensicAgent Tasks
——Tier 310FB 2026Pending
ReverseEngBench
Forensic
——Tier 310FB 2026Pending
Tax Agent Bench
ForensicAgent Tasks
66.0#3 / 25Tier 310FB 20262026-09
Big Finance Bench
ForensicDocument QA
——Tier 310FB 2026Pending
GDPval-MM
Document QANumerical
——Tier 310FB 2026Pending
BankerToolBench
Agent Tasks
——Tier 310FB 2026Pending
GDPval-Rubrics
Forensic
——Tier 310FB 2026Pending
PRBench-Finance
NumericalForensic
——Tier 310FB 2026Pending
CorpFin
ForensicVerification
——Tier 220FB 2026Pending
Contents.md
Model info
OrganisationAlibaba
Release date2026-08-03
LicenseOpen-weight
Context window1M tokens
Open weightYes
FB Score breakdown
Finance Agent×30 = 15.2
VALS Index×25 = 13.0
MortgageTax×20 = 12.8
TaxEval v2×20 = 15.1
Code Migration×10 = 2.4
EMB×10 = 6.0
Legal Research×10 = 4.8
MedCode×10 = 4.1
MedScribe×10 = 8.5
ProofBench×10 = 5.8
SAGE×10 = 5.1
Public Benefits×10 = 6.7
Vibe Code Bench×10 = 6.5
Harvey Legal×10 = 1.0
GPQA Diamond×15 = 14.1
IOI×10 = 7.3
LiveCodeBench×10 = 8.8
LegalBench×10 = 8.4
MMLU Pro×15 = 13.3
MMMU×10 = 8.8
ProgramBench×10 = 0.0
SkillsBench×10 = 4.2
SWE-bench×20 = 17.1
Terminal-Bench×10 = 6.7
Tax Agent×10 = 6.6
FB Score (weighted avg)62.2
Compare - all models
AClaude Opus 4.773.8%
OGPT-5.572.2%
OGPT-6 Sol71.1%
DDeepSeek V4 Pro70.1%
GGemini 3.1 Pro70.0%
OGPT-6 Luna70.0%
Compare vs Claude Opus 4.7 in full →
Evaluation notes
Scores reflect median of 3 runs per task at temperature 0.0 with 0-shot prompting. PAVE evaluation conducted by FinanceBenchmark. Other scores sourced from latest published arXiv papers.