Benchmarks · /benchmarks/vals-ai-tax_eval_v2

TaxEval v2

Name: TaxEval v2
Creator: Vals AI

TaxEval v2 result as reported by Vals AI.

Source · Vals AI
Version · vals-ai snapshot 2026-06-24
Scores · 92

Test details

Visible tradeoffsThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Vals AI

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

vals_tax_eval_v2_current

domain

Professional reasoning

What it measures vs what it misses

✓ Measures

Answer quality on tax questions and responses.

✗ Misses

Adjacent skills outside the benchmark task mix, latency, and cost.

Why this countsAnswer quality on tax questions and responses.Same-test ruleThis percentile only compares models inside the exact benchmark/version group shown here. It is not a universal score.What it missesAdjacent skills outside the benchmark task mix, latency, and cost.

Leaderboard · this benchmark version

#1 · muse-spark

VALS-AI · Jun 17, 2026

Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Meta.

77.7%76.1% - 79.3%

#2 · Claude Sonnet 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

77.1%75.5% - 78.7%

#3 · Claude Fable 5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

76.9%75.3% - 78.6%

#4 · Claude Opus 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-6-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 96.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

76%74.3% - 77.6%

#5 · Grok 3

VALS-AI · Jun 17, 2026

Source label: grok/grok-3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 95.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

75.9%74.3% - 77.5%

#6 · GPT-5.2

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.2-2025-12-11

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 94.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.8%74.1% - 77.4%

#7 · Grok 4 Fast

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-fast-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

75.7%74.2% - 77.2%

#8 · Claude Opus 4.8

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

75.6%74% - 77.3%

#9 · Qwen3.7 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 91.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

75.3%73.7% - 77%

#10 · Claude Opus 4.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

75.3%73.6% - 76.9%

#11 · GPT-5.4 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5-mini-2025-08-07

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 89%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.2%73.6% - 76.9%

#12 · GPT-4.1

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 87.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.1%73.4% - 76.7%

#13 · GPT-5.5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75%73.3% - 76.7%

#14 · GPT-5.1

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.1-2025-11-13

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 85.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.9%73.2% - 76.5%

#15 · Claude Opus 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-5-20251101-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 84.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

74.9%73.2% - 76.5%

#16 · o4 mini

VALS-AI · Jun 17, 2026

Source label: openai/o4-mini-2025-04-16

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 83.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.8%73.1% - 76.4%

#17 · qwen3.6-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

74.7%73.1% - 76.4%

#18 · kimi-k2.6

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 81.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

74.7%73% - 76.3%

#19 · o3

VALS-AI · Jun 17, 2026

Source label: openai/o3-2025-04-16

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 80.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.6%72.9% - 76.2%

#20 · GPT-4o

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4o-2024-11-20

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.5%72.8% - 76.2%

#21 · Gemini 3.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 78%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

74.4%72.7% - 76%

#22 · o1

VALS-AI · Jun 17, 2026

Source label: openai/o1-2024-12-17

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 76.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.3%72.6% - 76%

#23 · kimi-k2.5-thinking

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.5-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 75.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

74.2%72.5% - 75.9%

#24 · Grok 4.20

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.20-0309-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

74.1%72.4% - 75.8%

#25 · Claude Sonnet 3.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-7-sonnet-20250219-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 73.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

74%72.4% - 75.7%

#26 · Qwen3 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 72.5%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

74%72.3% - 75.6%

#27 · GPT-5.4

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-2026-03-05

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74%72.3% - 75.7%

#28 · Gemini 3 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-flash-preview

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 70.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

73.9%72.2% - 75.6%

#29 · mimo-v2.5-pro

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 69.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Xiaomi.

73.8%72.1% - 75.5%

#30 · Claude Opus 4.1

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-1-20250805-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 68.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

73.7%72% - 75.4%

#31 · GPT-5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 67%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

73.4%71.7% - 75.1%

#32 · GLM-5.2 (max)

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 65.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

73.3%71.6% - 75%

#33 · Claude Sonnet 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-5-20250929-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 64.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

73.3%71.6% - 75%

#34 · Grok 4.1 Fast

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-1-fast-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

73.1%71.4% - 74.8%

#35 · Nemotron 3 Ultra 550B A55B (Reasoning)

VALS-AI · Jun 17, 2026

Source label: nvidia/nemotron-3-ultra-550b-a55b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 62.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Nvidia.

73.1%71.4% - 74.8%

#36 · Mistral Large (Feb '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-large-2512

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 61.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

73.1%71.4% - 74.8%

#37 · Grok 3 mini

VALS-AI · Jun 17, 2026

Source label: grok/grok-3-mini-fast-low-reasoning

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 60.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

73%71.3% - 74.7%

#38 · Gemini 2.5 Pro

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-pro-exp-03-25

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9%71.2% - 74.6%

#39 · Gemini 3.1 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 58.2%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9%71.2% - 74.6%

#40 · Gemini 2.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-flash-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.7%71% - 74.4%

#41 · minimax-m3

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 57.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

72.7%71% - 74.4%

#42 · Gemini 3 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 54.9%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.6%70.9% - 74.3%

#43 · glm-4.5

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 53.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

72.4%70.7% - 74.1%

#44 · DeepSeek Reasoner

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

72.3%70.6% - 74%

#45 · Qwen3.5 Flash

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.5-flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 51.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

72.2%70.4% - 73.9%

#46 · deepseek-v4-pro

VALS-AI · Jun 17, 2026

Source label: deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 50.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: DeepSeek.

72.1%70.4% - 73.8%

#47 · Claude Sonnet 4

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-20250514-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 49.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

72%70.3% - 73.7%

#48 · GPT-4.1 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-mini-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 48.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

71.9%70.2% - 73.6%

#49 · Claude Opus 4

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-20250514

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 48.4%
Last updated: recent
Eligibility: historical_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

71.9%70.2% - 73.6%

#50 · mimo-v2.5

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 46.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Xiaomi.

71.8%70.1% - 73.6%

#51 · Gemini 3.1 Flash-Lite Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 45.1%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

71.8%70.1% - 73.5%

#52 · Kimi K2 Thinking

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 44%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

71.7%70% - 73.4%

#53 · GPT-OSS 120B

VALS-AI · Jun 17, 2026

Source label: fireworks/gpt-oss-120b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 42.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

71.6%69.9% - 73.3%

#54 · Qwen3.6 27B (Reasoning)

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-27b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 41.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

71.3%69.5% - 73%

#55 · glm-5.1

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 40.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

71.2%69.4% - 72.9%

#56 · deepseek-v3-0324

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-v3-0324

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 39.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

71.1%69.4% - 72.8%

#57 · Grok 4.3

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 38.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

70.8%69.1% - 72.6%

#58 · Qwen3 235B A22B

VALS-AI · Jun 17, 2026

Source label: fireworks/qwen3-235b-a22b

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 37.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

70.6%68.9% - 72.4%

#59 · mistral-medium-2505

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-2505

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 36.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

70.3%68.6% - 72.1%

#60 · kimi-k2-instruct

VALS-AI · Jun 17, 2026

Source label: together/moonshotai/Kimi-K2-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 35.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Together AI.

70.2%68.4% - 72%

#61 · Claude Sonnet 3.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-5-sonnet-20241022

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 34.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

70.2%68.4% - 71.9%

#62 · glm-5

VALS-AI · Jun 17, 2026

Source label: zai/glm-5-thinking

verified runtimeexact directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 33%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: exact (1.00)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

70%68.3% - 71.8%

#63 · Gemini 2.0 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.0-flash-thinking-exp-01-21

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 31.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

69.8%68% - 71.6%

#64 · o3 mini

VALS-AI · Jun 17, 2026

Source label: openai/o3-mini-2025-01-31

verified runtimeexact directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 30.8%
Last updated: recent
Eligibility: historical_model
Identity: exact (1.00)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

69.4%67.6% - 71.2%

#65 · glm-4.7

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 29.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

68.8%67% - 70.6%

#66 · Gemini 2.0 Pro Experimental

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.0-pro-exp-02-05

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 28.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

68.2%66.4% - 69.9%

#67 · minimax-m2.5

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 28.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

68.2%66.4% - 69.9%

#68 · mistral-medium-3.5

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 26.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

68%66.2% - 69.8%

#69 · deepseek-v3

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-v3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 25.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

67.9%66.1% - 69.7%

#70 · Claude Haiku 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

67.5%65.7% - 69.3%

#71 · GPT-5.4 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-nano-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 23.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

67.4%65.6% - 69.2%

#72 · Grok 2

VALS-AI · Jun 17, 2026

Source label: grok/grok-2-1212

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 22%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

67%65.2% - 68.8%

#73 · minimax-m2.7

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 20.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

66.6%64.8% - 68.4%

#74 · MiniMax-M2.1

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 19.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

66.4%64.5% - 68.2%

#75 · glm-4.6

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 18.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

66.2%64.7% - 67.8%

#76 · Gemini 2.5 Flash-Lite

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

66.2%64.4% - 68%

#77 · Grok 4

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-0709

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 16.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

65.1%63.2% - 67%

#78 · mistral-large-2411

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-large-2411

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 15.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

63.8%61.9% - 65.6%

#79 · GPT-OSS 20B

VALS-AI · Jun 17, 2026

Source label: fireworks/gpt-oss-20b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 14.3%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

63.7%61.9% - 65.5%

#80 · Magistral Medium 1.2

VALS-AI · Jun 17, 2026

Source label: mistralai/magistral-medium-2509

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 13.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

61.9%60% - 63.8%

#81 · command-a-03-2025

VALS-AI · Jun 17, 2026

Source label: cohere/command-a-03-2025

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 12.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Cohere.

61.4%59.5% - 63.2%

#82 · GPT-4.1 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-nano-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 11%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

60.8%58.9% - 62.6%

#83 · GPT-4o mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4o-mini-2024-07-18

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 9.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

60.5%58.7% - 62.4%

#84 · Magistral Small 1.2

VALS-AI · Jun 17, 2026

Source label: mistralai/magistral-small-2509

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 8.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

60.3%58.4% - 62.2%

#85 · Gemini 1.5 Pro

VALS-AI · Jun 17, 2026

Source label: google/gemini-1.5-pro-002

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 7.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

59.5%57.6% - 61.4%

#86 · Mistral Small (Sep '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-small-2503

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 6.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

58.3%56.4% - 60.2%

#87 · jamba-1.5-large

VALS-AI · Jun 17, 2026

Source label: ai21labs/jamba-1.5-large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 5.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: AI21 Labs.

58.2%56.3% - 60.1%

#88 · Claude Haiku 3.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-5-haiku-20241022

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 4.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

57.4%55.4% - 59.3%

#89 · llama-4-scout-17b-16e-instruct

VALS-AI · Jun 17, 2026

Source label: together/meta-llama/Llama-4-Scout-17B-16E-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 3.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Together AI.

55.2%53.3% - 57.1%

#90 · Mistral Small (Feb '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-small-2402

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 2.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

49.1%47.2% - 51.1%

#91 · Gemini 1.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-1.5-flash-002

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 1.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

48.2%46.3% - 50.1%

#92 · jamba-1.5-mini

VALS-AI · Jun 17, 2026

Source label: ai21labs/jamba-1.5-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: AI21 Labs.

41.9%40% - 43.8%

Benchmarks · /benchmarks/vals-ai-tax_eval_v2

TaxEval v2

TaxEval v2 result as reported by Vals AI.

Source · Vals AI
Version · vals-ai snapshot 2026-06-24
Scores · 92

Test details

Visible tradeoffsThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Vals AI

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

vals_tax_eval_v2_current

domain

Professional reasoning

What it measures vs what it misses

✓ Measures

Answer quality on tax questions and responses.

✗ Misses

Adjacent skills outside the benchmark task mix, latency, and cost.

Leaderboard · this benchmark version

#1 · muse-spark

VALS-AI · Jun 17, 2026

Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Meta.

77.7%76.1% - 79.3%

#2 · Claude Sonnet 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

77.1%75.5% - 78.7%

#3 · Claude Fable 5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

76.9%75.3% - 78.6%

#4 · Claude Opus 4.6

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-6-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 96.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

76%74.3% - 77.6%

#5 · Grok 3

VALS-AI · Jun 17, 2026

Source label: grok/grok-3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 95.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

75.9%74.3% - 77.5%

#6 · GPT-5.2

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.2-2025-12-11

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 94.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.8%74.1% - 77.4%

#7 · Grok 4 Fast

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-fast-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

75.7%74.2% - 77.2%

#8 · Claude Opus 4.8

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

75.6%74% - 77.3%

#9 · Qwen3.7 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.7-max

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 91.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

75.3%73.7% - 77%

#10 · Claude Opus 4.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

75.3%73.6% - 76.9%

#11 · GPT-5.4 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5-mini-2025-08-07

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 89%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.2%73.6% - 76.9%

#12 · GPT-4.1

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 87.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75.1%73.4% - 76.7%

#13 · GPT-5.5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

75%73.3% - 76.7%

#14 · GPT-5.1

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.1-2025-11-13

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 85.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.9%73.2% - 76.5%

#15 · Claude Opus 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-5-20251101-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 84.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

74.9%73.2% - 76.5%

#16 · o4 mini

VALS-AI · Jun 17, 2026

Source label: openai/o4-mini-2025-04-16

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 83.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.8%73.1% - 76.4%

#17 · qwen3.6-plus

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

74.7%73.1% - 76.4%

#18 · kimi-k2.6

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 81.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

74.7%73% - 76.3%

#19 · o3

VALS-AI · Jun 17, 2026

Source label: openai/o3-2025-04-16

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 80.2%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.6%72.9% - 76.2%

#20 · GPT-4o

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4o-2024-11-20

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.5%72.8% - 76.2%

#21 · Gemini 3.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.5-flash

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 78%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

74.4%72.7% - 76%

#22 · o1

VALS-AI · Jun 17, 2026

Source label: openai/o1-2024-12-17

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 76.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74.3%72.6% - 76%

#23 · kimi-k2.5-thinking

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2.5-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 75.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

74.2%72.5% - 75.9%

#24 · Grok 4.20

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.20-0309-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 74.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

74.1%72.4% - 75.8%

#25 · Claude Sonnet 3.7

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-7-sonnet-20250219-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 73.6%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

74%72.4% - 75.7%

#26 · Qwen3 Max

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 72.5%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

74%72.3% - 75.6%

#27 · GPT-5.4

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-2026-03-05

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 72.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

74%72.3% - 75.7%

#28 · Gemini 3 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-flash-preview

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 70.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

73.9%72.2% - 75.6%

#29 · mimo-v2.5-pro

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 69.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Xiaomi.

73.8%72.1% - 75.5%

#30 · Claude Opus 4.1

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-1-20250805-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 68.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

73.7%72% - 75.4%

#31 · GPT-5

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5-2025-08-07

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 67%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

73.4%71.7% - 75.1%

#32 · GLM-5.2 (max)

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.2

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 65.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

73.3%71.6% - 75%

#33 · Claude Sonnet 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-5-20250929-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 64.8%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

73.3%71.6% - 75%

#34 · Grok 4.1 Fast

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-1-fast-reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

73.1%71.4% - 74.8%

#35 · Nemotron 3 Ultra 550B A55B (Reasoning)

VALS-AI · Jun 17, 2026

Source label: nvidia/nemotron-3-ultra-550b-a55b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 62.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Nvidia.

73.1%71.4% - 74.8%

#36 · Mistral Large (Feb '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-large-2512

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 61.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

73.1%71.4% - 74.8%

#37 · Grok 3 mini

VALS-AI · Jun 17, 2026

Source label: grok/grok-3-mini-fast-low-reasoning

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 60.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

73%71.3% - 74.7%

#38 · Gemini 2.5 Pro

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-pro-exp-03-25

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9%71.2% - 74.6%

#39 · Gemini 3.1 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 58.2%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9%71.2% - 74.6%

#40 · Gemini 2.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-flash-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.7%71% - 74.4%

#41 · minimax-m3

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 57.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

72.7%71% - 74.4%

#42 · Gemini 3 Pro Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 54.9%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.6%70.9% - 74.3%

#43 · glm-4.5

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 53.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

72.4%70.7% - 74.1%

#44 · DeepSeek Reasoner

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

72.3%70.6% - 74%

#45 · Qwen3.5 Flash

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.5-flash

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 51.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

72.2%70.4% - 73.9%

#46 · deepseek-v4-pro

VALS-AI · Jun 17, 2026

Source label: deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 50.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: DeepSeek.

72.1%70.4% - 73.8%

#47 · Claude Sonnet 4

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-sonnet-4-20250514-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 49.5%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

72%70.3% - 73.7%

#48 · GPT-4.1 mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-mini-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 48.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

71.9%70.2% - 73.6%

#49 · Claude Opus 4

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-opus-4-20250514

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 48.4%
Last updated: recent
Eligibility: historical_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

71.9%70.2% - 73.6%

#50 · mimo-v2.5

VALS-AI · Jun 17, 2026

Source label: xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 46.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Xiaomi.

71.8%70.1% - 73.6%

#51 · Gemini 3.1 Flash-Lite Preview

VALS-AI · Jun 17, 2026

Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 45.1%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

71.8%70.1% - 73.5%

#52 · Kimi K2 Thinking

VALS-AI · Jun 17, 2026

Source label: kimi/kimi-k2-thinking

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 44%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Moonshot AI.

71.7%70% - 73.4%

#53 · GPT-OSS 120B

VALS-AI · Jun 17, 2026

Source label: fireworks/gpt-oss-120b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 42.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

71.6%69.9% - 73.3%

#54 · Qwen3.6 27B (Reasoning)

VALS-AI · Jun 17, 2026

Source label: alibaba/qwen3.6-27b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 41.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Alibaba.

71.3%69.5% - 73%

#55 · glm-5.1

VALS-AI · Jun 17, 2026

Source label: zai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 40.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

71.2%69.4% - 72.9%

#56 · deepseek-v3-0324

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-v3-0324

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 39.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

71.1%69.4% - 72.8%

#57 · Grok 4.3

VALS-AI · Jun 17, 2026

Source label: grok/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 38.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

70.8%69.1% - 72.6%

#58 · Qwen3 235B A22B

VALS-AI · Jun 17, 2026

Source label: fireworks/qwen3-235b-a22b

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 37.4%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

70.6%68.9% - 72.4%

#59 · mistral-medium-2505

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-2505

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 36.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

70.3%68.6% - 72.1%

#60 · kimi-k2-instruct

VALS-AI · Jun 17, 2026

Source label: together/moonshotai/Kimi-K2-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 35.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Together AI.

70.2%68.4% - 72%

#61 · Claude Sonnet 3.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-5-sonnet-20241022

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 34.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

70.2%68.4% - 71.9%

#62 · glm-5

VALS-AI · Jun 17, 2026

Source label: zai/glm-5-thinking

verified runtimeexact directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 33%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: exact (1.00)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

70%68.3% - 71.8%

#63 · Gemini 2.0 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.0-flash-thinking-exp-01-21

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 31.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

69.8%68% - 71.6%

#64 · o3 mini

VALS-AI · Jun 17, 2026

Source label: openai/o3-mini-2025-01-31

verified runtimeexact directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 30.8%
Last updated: recent
Eligibility: historical_model
Identity: exact (1.00)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

69.4%67.6% - 71.2%

#65 · glm-4.7

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 29.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

68.8%67% - 70.6%

#66 · Gemini 2.0 Pro Experimental

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.0-pro-exp-02-05

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 28.6%
Last updated: recent
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

68.2%66.4% - 69.9%

#67 · minimax-m2.5

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 28.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

68.2%66.4% - 69.9%

#68 · mistral-medium-3.5

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-medium-3.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 26.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

68%66.2% - 69.8%

#69 · deepseek-v3

VALS-AI · Jun 17, 2026

Source label: fireworks/deepseek-v3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 25.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

67.9%66.1% - 69.7%

#70 · Claude Haiku 4.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

67.5%65.7% - 69.3%

#71 · GPT-5.4 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-5.4-nano-2026-03-17

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 23.1%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

67.4%65.6% - 69.2%

#72 · Grok 2

VALS-AI · Jun 17, 2026

Source label: grok/grok-2-1212

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 22%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

67%65.2% - 68.8%

#73 · minimax-m2.7

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 20.9%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

66.6%64.8% - 68.4%

#74 · MiniMax-M2.1

VALS-AI · Jun 17, 2026

Source label: minimax/MiniMax-M2.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 19.8%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: MiniMax.

66.4%64.5% - 68.2%

#75 · glm-4.6

VALS-AI · Jun 17, 2026

Source label: zai/glm-4.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 18.7%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Zhipu AI.

66.2%64.7% - 67.8%

#76 · Gemini 2.5 Flash-Lite

VALS-AI · Jun 17, 2026

Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

66.2%64.4% - 68%

#77 · Grok 4

VALS-AI · Jun 17, 2026

Source label: grok/grok-4-0709

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 16.5%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: xAI.

65.1%63.2% - 67%

#78 · mistral-large-2411

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-large-2411

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 15.4%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

63.8%61.9% - 65.6%

#79 · GPT-OSS 20B

VALS-AI · Jun 17, 2026

Source label: fireworks/gpt-oss-20b

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 14.3%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

63.7%61.9% - 65.5%

#80 · Magistral Medium 1.2

VALS-AI · Jun 17, 2026

Source label: mistralai/magistral-medium-2509

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 13.2%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

61.9%60% - 63.8%

#81 · command-a-03-2025

VALS-AI · Jun 17, 2026

Source label: cohere/command-a-03-2025

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 12.1%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Cohere.

61.4%59.5% - 63.2%

#82 · GPT-4.1 nano

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4.1-nano-2025-04-14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 11%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

60.8%58.9% - 62.6%

#83 · GPT-4o mini

VALS-AI · Jun 17, 2026

Source label: openai/gpt-4o-mini-2024-07-18

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 9.9%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: OpenAI.

60.5%58.7% - 62.4%

#84 · Magistral Small 1.2

VALS-AI · Jun 17, 2026

Source label: mistralai/magistral-small-2509

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 8.8%
Last updated: recent
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

60.3%58.4% - 62.2%

#85 · Gemini 1.5 Pro

VALS-AI · Jun 17, 2026

Source label: google/gemini-1.5-pro-002

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 7.7%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

59.5%57.6% - 61.4%

#86 · Mistral Small (Sep '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-small-2503

verified runtimevariant directBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 6.6%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: dated variant (0.80)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

58.3%56.4% - 60.2%

#87 · jamba-1.5-large

VALS-AI · Jun 17, 2026

Source label: ai21labs/jamba-1.5-large

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 5.5%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: AI21 Labs.

58.2%56.3% - 60.1%

#88 · Claude Haiku 3.5

VALS-AI · Jun 17, 2026

Source label: anthropic/claude-3-5-haiku-20241022

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 4.4%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

57.4%55.4% - 59.3%

#89 · llama-4-scout-17b-16e-instruct

VALS-AI · Jun 17, 2026

Source label: together/meta-llama/Llama-4-Scout-17B-16E-Instruct

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 3.3%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Together AI.

55.2%53.3% - 57.1%

#90 · Mistral Small (Feb '24)

VALS-AI · Jun 17, 2026

Source label: mistralai/mistral-small-2402

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 2.2%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Mistral AI.

49.1%47.2% - 51.1%

#91 · Gemini 1.5 Flash

VALS-AI · Jun 17, 2026

Source label: google/gemini-1.5-flash-002

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 1.1%
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

48.2%46.3% - 50.1%

#92 · jamba-1.5-mini

VALS-AI · Jun 17, 2026

Source label: ai21labs/jamba-1.5-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.vals.ai/benchmarks/tax_eval_v2
Percentile: 0%
Last updated: recent
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: AI21 Labs.

41.9%40% - 43.8%

TaxEval v2

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

TaxEval v2

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version