BasedAGIBasedAGI
Menu
Rankings live

supply_chain

Tail spend categorization

Categorize tail spend purchases into taxonomy buckets for sourcing.

#1 Recommendation

gpt-4.1-20250414

Strong on OpenVLM OCRBench Official ocrbench_score_pct (88%) and Galileo Agent Leaderboard v2 Avg TSQ (64%)

external/openai/gpt-4-1-20250414

20.3%

Score

30.8%

Confidence

Limited benchmark evidence for this use case.

32 ranked models with average evidence of 13.5 points. Rankings may shift as more benchmark data is ingested.

Ranked Models

30

Evidence Quality

79%

Scoring

Benchmark-backed

Top Signal

OpenVLM OCRBench Official: ocrbench_score_pct

All Ranked Models

Max params:
Min confidence:
30 of 30
RankModelScore
#1gpt-4.1-20250414

Strong on OpenVLM OCRBench Official ocrbench_score_pct (88%) and Galileo Agent Leaderboard v2 Avg TSQ (64%)

20.3%
#2gemini-2.5-flash

Strong on Galileo Agent Leaderboard v2 Avg TSQ (100%) and LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct (100%)

17.5%
#4gpt-4.1-mini-20250414
16.9%
#5gpt-4o
16.7%
#6gemini-2.5-pro
16.3%
#15qwen-2.5-72b-instruct
12.8%
#17gemini-3-pro-preview
11.9%
#18Grok-4-0709
11.8%
#19google/gemini-2.0-flash-001
11.8%
#21claude-sonnet-4-20250514
11.7%
#24gpt-5-2025-08-07
11.5%
#27gpt-5-mini-2025-08-07
10.8%
#35deepseek/deepseek-r1
10.2%
#41google/gemini-3.1-pro-preview
9.6%
#46anthropic/claude-sonnet-4.6
9.2%
#66openai/gpt-5.4-2026-03-05
8.6%
#73gpt-5.1-2025-11-13
8.4%
#78claude-opus-4-5-20251101
8.3%
#83Llama-3.1-70B-Instruct
8.0%
#88Qwen3-Embedding-4B
7.9%
#93GPT-4.1-nano-2025-04-14
7.9%
#97Llama-3.3-70B-Instruct
7.9%
#110Qwen-VL-Chat
7.6%
#114kimi/kimi-k2.5-thinking
7.5%
#135xai-org/grok-4-fast-reasoning
6.9%
#147openai/gpt-4o-mini-2024-07-18
6.7%
#150phi-4
6.7%
#155gpt-4o-2024-08-06
6.6%
#165xai-org/grok-4-1-fast-reasoning
6.5%
#196gpt-4o-2024-05-13
6.0%

Compare Models

Model A leads by +2.9%

Shareable Link →

Model A

gpt-4.1-20250414

external/openai/gpt-4-1-20250414

20.3%

Rank #1

Confidence 30.8%23 evidence pts

OpenVLM OCRBench Official: ocrbench_score_pct

Value 87.7% · Conf 100.0% · Weight 2.2%

openvlm_ocrbench_official.ocrbench_score_pct (Mar 12, 2026)

Galileo Agent Leaderboard v2: Avg TSQ

Value 64.1% · Conf 100.0% · Weight 2.0%

galileo_agent_v2.avg_tsq (Mar 12, 2026)

OpenVLM TextVQA Official: textvqa_score_pct

Value 76.8% · Conf 100.0% · Weight 2.0%

openvlm_textvqa_official.textvqa_score_pct (Mar 12, 2026)

Galileo Agent Leaderboard v2: Avg AC

Value 100.0% · Conf 100.0% · Weight 1.8%

galileo_agent_v2.avg_ac (Mar 12, 2026)

Model B

gemini-2.5-flash

external/google/gemini-2-5-flash

17.5%

Rank #2

Confidence 22.0%16 evidence pts

Galileo Agent Leaderboard v2: Avg TSQ

Value 100.0% · Conf 100.0% · Weight 3.1%

galileo_agent_v2.avg_tsq (Mar 12, 2026)

LanguageBench Grammar/Clarity Official (Split): grammar_clarity_score_pct

Value 100.0% · Conf 100.0% · Weight 2.2%

languagebench_grammar_clarity_official.grammar_clarity_score_pct (Mar 12, 2026)

LanguageBench Translation Official (Split): translation_to:bleu

Value 92.0% · Conf 100.0% · Weight 2.0%

languagebench_translation_official.translation_to_bleu (Mar 12, 2026)

LanguageBench: overall:mean

Value 100.0% · Conf 100.0% · Weight 2.0%

languagebench.overall_mean (Mar 12, 2026)

Ranking Diagnostics & Missing Models

Source Lift

Ranked

32

Sources

8

Quality

Insufficient

Vals MedQA

vals_medqa

20 rows

0.5% avg lift

Vals Tax Eval v2

vals_tax_eval_v2

20 rows

0.5% avg lift

Vals CorpFin v2

vals_corp_fin_v2

20 rows

0.4% avg lift

Vals Legal Bench

vals_legal_bench

19 rows

0.5% avg lift

Missing Strong Models

gemini-3-flash-preview

external/google/gemini-3-flash-preview

Rank #15

16.2%

Thin evidence after weighting

gpt-5.2-2025-12-11

external/openai/gpt-5-2-2025-12-11

Rank #16

16.2%

Thin evidence after weighting

anthropic/claude-opus-4-6-thinking

external/anthropic/claude-opus-4-6-thinking

Rank #17

16.1%

Thin evidence after weighting

google/gemini-3.1-flash-lite-preview

external/google/gemini-3-1-flash-lite-preview

Rank #19

15.6%

Thin evidence after weighting
Taxonomy Details

Core Tasks

task.topic_taggingtask.intent_classification

Required Modes

mode.json_schema

Domains

domain.procurement_vendor_mgmt

Related Use Cases