Skip to main content

Benchmark profile

Vals TaxEval v2 (TaxEval v2)

A Vals-created set of questions and responses to tax questions

Data verified

How BenchLM shows TaxEval v2

BenchLM mirrors the public Vals AI TaxEval v2 leaderboard captured from https://www.vals.ai/benchmarks/tax_eval_v2 and updated by Vals on July 17, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

TaxEval v2 is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

129 Vals rows3 task viewsprivate datasetTasks: Overall, Correctness, Stepwise ReasoningDisplay only

TaxEval v2 score on TaxEval v2 — July 17, 2026

BenchLM mirrors the published taxeval v2 score view for TaxEval v2. Muse Spark 1 1 leads the public snapshot at 79.72% , followed by Muse Spark (77.68%) and Claude Sonnet 4.6 (77.11%). BenchLM does not use these results to rank models overall.

129 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 17, 2026

TaxEval v2 score table (129 models)

Score
1
79.72%
2
77.68%
3
77.11%
4
76.94%
5
76.17%
6
76.17%
7
75.96%
8
Grok 3SpaceXAI
75.88%
9
GPT-5.2OpenAI
75.76%
10
Kimi K3Moonshot AI
75.72%
11
75.70%
12
75.63%
13
75.63%
14
75.31%
15
InklingThinkingmachines
75.31%
16
75.27%
17
75.22%
18
GPT-4.1OpenAI
75.06%
19
GPT-5.5OpenAI
74.98%
20
GPT-5.1OpenAI
74.86%
22
O4 MiniOpenAI
74.78%
23
74.78%
24
74.73%
25
Kimi K2.6Moonshot AI
74.65%
26
O3OpenAI
74.57%
27
GPT-4oOpenAI
74.53%
28
74.37%
29
74.33%
30
O1OpenAI
74.28%
31
74.20%
32
74.12%
34
73.96%
35
GPT-5.4OpenAI
73.96%
37
73.79%
39
Qwen3 MaxAlibaba
73.51%
40
GPT-5OpenAI
73.39%
41
GLM 5.2Zhipu AI
73.34%
43
73.14%
45
73.06%
50
MiniMax M3MiniMax
72.73%
51
72.57%
52
72.40%
54
GLM 4.5Zhipu AI
72.40%
55
DeepSeek R1Fireworks AI
72.28%
56
72.16%
57
72.08%
59
71.91%
60
Claude Opus 4Anthropic
71.91%
61
Mimo V2.5Xiaomi
71.83%
63
Kimi K2 ThinkingMoonshot AI
71.71%
64
Grok 4.5SpaceXAI
71.67%
65
GPT Oss 120bFireworks AI
71.59%
67
71.46%
68
71.26%
69
71.22%
70
GLM 5.1Zhipu AI
71.19%
72
GPT-4oOpenAI
71.14%
74
DeepSeek V3 0324Fireworks AI
71.10%
75
Grok 4.3SpaceXAI
70.81%
76
Qwen3 235b A22bFireworks AI
70.65%
78
70.32%
79
70.20%
80
70.16%
81
70.03%
83
69.62%
84
O3 MiniOpenAI
69.42%
85
GLM 4.7Zhipu AI
68.77%
87
68.15%
88
68.15%
89
67.99%
90
DeepSeek V3Fireworks AI
67.91%
91
67.74%
93
67.42%
94
67.38%
95
Grok 2 1212SpaceXAI
67.05%
96
66.56%
97
66.56%
98
66.35%
99
GLM 4.6Zhipu AI
66.23%
101
65.25%
102
Grok 4 0709SpaceXAI
65.09%
104
63.78%
106
GPT Oss 20bFireworks AI
63.70%
107
61.94%
109
61.37%
110
60.88%
112
60.75%
113
60.55%
114
60.30%
116
Laguna Xs.2Poolside
59.98%
117
59.48%
119
58.30%
120
58.18%
121
57.36%
124
49.14%
125
48.20%
126
44.60%
127
41.86%
129
Laguna M.1Poolside
1.64%

The published TaxEval v2 snapshot places Muse Spark 1 1 first at 79.72%. The third row is 2.62 points behind. The broader top-10 range is 4.01 points, so many of the published results sit in a relatively narrow band.

129 models have been evaluated on TaxEval v2. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. TaxEval v2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About TaxEval v2

Year

2026

Tasks

Tax question answering and response evaluation

Format

Accuracy score

Difficulty

Professional tax reasoning

BenchLM mirrors the public Vals AI TaxEval v2 leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

TaxEval v2 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does TaxEval v2 measure?

A Vals-created set of questions and responses to tax questions

Which model leads the published TaxEval v2 snapshot?

Muse Spark 1 1 currently leads the published TaxEval v2 snapshot with 79.72% taxeval v2 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on TaxEval v2?

129 AI models are included in BenchLM's mirrored TaxEval v2 snapshot, based on the public leaderboard captured on July 17, 2026.

Last updated: July 17, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.