Productivity

Text tagging and routing

Tag and classify text for organization and workflow routing.

task.topic_taggingtask.intent_classification

Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

gemini-2.5-pro

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

24.0%

Best benchmark score

41.2%

Confidence

All ranked models — top 3

🥇

gemini-2.5-pro

24.0%

🥈

gemini-3.1-pro-preview

23.4%

🥉

gpt-4.1-20250414

22.6%

Ranked Models

Evidence Quality

81%

Evidence Points

Top Signal

Galileo Agent Leaderboard v2: Avg TSQ

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	gemini-2.5-pro Strong on Galileo Agent Leaderboard v2 Avg TSQ and OpenVLM OCRBench Official ocrbench_score_pct	24.0%	41%	$3.44	Galileo Agent Leaderboard v2OpenVLM OCRBench Official
🥈	gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct	23.4%	27%	$4.50	Vals Finance AgentSimpleQA Verified
🥉	gpt-4.1-20250414 Strong on OpenVLM OCRBench Official ocrbench_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	22.6%	34%	—	OpenVLM OCRBench OfficialGalileo Agent Leaderboard v2
#4	claude-sonnet-4 Strong on LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	22.5%	32%	$6.00	LanguageBench Grammar/Clarity Official (Split)Galileo Agent Leaderboard v2
#5	gpt-5-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and OpenVLM OCRBench Official ocrbench_score_pct	21.4%	28%	—	Vals Finance AgentOpenVLM OCRBench Official
#6	gemini-2.5-flash Strong on LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	21.3%	30%	$0.17	LanguageBench Grammar/Clarity Official (Split)Galileo Agent Leaderboard v2
#7	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and OpenVLM OCRBench Official ocrbench_score_pct	21.0%	32%	—	Vals Finance AgentOpenVLM OCRBench Official
#8	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vals Finance Agent overall_accuracy_pct	18.0%	27%	—	Galileo Agent Leaderboard v2Vals Finance Agent
#9	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct	17.1%	25%	$4.50	Vals Finance AgentSimpleQA Verified
#10	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct	16.6%	21%	$6.00	Vals Finance AgentVals Finance Agent
#11	Claude-3.5-Sonnet Strong on LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct and LLM-AggreFact Leaderboard average_score_pct	16.3%	20%	$6.00	LanguageBench Grammar/Clarity Official (Split)LLM-AggreFact Leaderboard
#12	gpt-5.2-2025-12-11 Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	16.1%	19%	—	Vals Finance AgentFACTS Benchmark Suite
#13	gemini-3.1-flash-lite-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	16.0%	24%	$0.56	Vals Finance AgentVals Mortgage Tax
#14	gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	16.0%	21%	—	Vals Finance AgentVals Mortgage Tax
#15	gemini-3-flash-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite average_score_pct	15.1%	23%	$1.13	Vals Finance AgentFACTS Benchmark Suite
#16	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals Case Law v2 overall_accuracy_pct	14.5%	21%	—	Vals Finance AgentVals Case Law v2
#18	gpt-4.1-mini-20250414 Strong on OpenVLM OCRBench Official ocrbench_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	14.0%	21%	—	OpenVLM OCRBench OfficialGalileo Agent Leaderboard v2
#19	claude-opus-4-5-20251101 Strong on Vals Mortgage Tax overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	13.5%	20%	—	Vals Mortgage TaxFACTS Benchmark Suite
#20	gpt-4o Strong on CRMArena Function Calling overall_score_pct and OpenVLM OCRBench Official ocrbench_score_pct	13.0%	16%	$0.26	CRMArena Function CallingOpenVLM OCRBench Official
#21	o3-20250416 Strong on Vals Mortgage Tax overall_accuracy_pct and SciArena Leaderboard rating_elo	12.9%	19%	$3.50	Vals Mortgage TaxSciArena Leaderboard
#22	grok-4-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct	12.4%	27%	$0.28	Vals Finance AgentVals Finance Agent
#23	gpt-4.1 Strong on LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct and DuckDB NSQL Leaderboard all_execution_accuracy	12.0%	15%	$3.50	LanguageBench Grammar/Clarity Official (Split)DuckDB NSQL Leaderboard
#25	claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	11.6%	13%	—	Vals Finance AgentVals Mortgage Tax
#26	gemini-2.0-flash-001 Strong on LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct and LanguageBench Translation Official (Split) translation_to:bleu	11.5%	15%	—	LanguageBench Grammar/Clarity Official (Split)LanguageBench Translation Official (Split)
#27	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	10.8%	13%	—	Vals Finance AgentVals Mortgage Tax
#30	kimi-k2.5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	10.4%	16%	—	Vals Finance AgentVals Mortgage Tax
#31	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	10.2%	13%	—	Vals Finance AgentVals Mortgage Tax
#32	grok-4-1-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard business_answer_rate_pct	10.0%	18%	$0.28	Vals Finance AgentVectara HHEM Leaderboard
#33	qwen-2.5-72b-instruct Strong on Galileo Agent Leaderboard v2 Avg TSQ and DuckDB NSQL Leaderboard all_execution_accuracy	10.0%	15%	—	Galileo Agent Leaderboard v2DuckDB NSQL Leaderboard
#34	claude-opus-4-1-20250805 Strong on Vals Mortgage Tax overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	9.9%	19%	—	Vals Mortgage TaxVectara HHEM Leaderboard

Compare Models

Select two different models above to compare their evidence side by side.

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

Vals Mortgage Tax

37 rows · 1.3% avg lift

Vals Legal Bench

36 rows · 0.4% avg lift

Vals MedQA

36 rows · 0.4% avg lift

Vals Tax Eval v2

34 rows · 0.4% avg lift

Missing frontier models

No obvious gaps right now.

▶Taxonomy & task details

Core tasks

task.topic_taggingtask.intent_classification

Required modes

mode.json_schema

Domains

domain.general_business

Related in Productivity

Knowledge base Q&A (fast, no citations)

Answer KB questions grounded in retrieved text without citations.

Knowledge base Q&A (with citations)

Answer questions grounded in an internal KB, with evidence.

Document summarization

Summarize long business documents into scannable outputs.

Decision memo

Recommend a decision with options, constraints, and risks.