/best/tabular-dataupdated August 2026131 models evaluated

Best AI for tabular data & spreadsheets

Reading, reasoning over, and extracting values from tables, CSVs, and spreadsheets.

CodingMathWritingResearchTranslationData AnalysisChatbotsStudentsBusinessCreative WritingTabular Data & Spreadsheets

Everyone who's pasted a spreadsheet into an LLM knows the failure mode: the model confidently returns a number from the wrong row, miscounts columns, or hallucinates a value from an adjacent cell. Tabular comprehension is one of the most practically important capabilities, and one of the least benchmarked.

Our test uses three escalating prompts: a clean 15-row CSV with multi-step arithmetic questions, a messy markdown table with ambiguity traps (two employees with the same name but different IDs, mixed date formats, a false alarm row that should be excluded), and a cross-reference task requiring joins across two related tables. Every question has a single unambiguous correct answer verified against ground truth.

The results are surprising. Budget models like Qwen3.5-9B ($0.15/MTok) and DeepSeek V4 Flash ($0.28) score a perfect 5/5, matching frontier models costing 100× more. The real differentiation comes on the cross-reference prompt — mid-tier models that ace the first two prompts start making arithmetic errors when they need to join tables and aggregate across them. If your use case involves pasting CSVs or financial reports into an LLM, this benchmark tells you exactly which models you can trust.

Full rankings

All 131 models, scored for tabular data & spreadsheets

weighted composite · lower-is-worse
#ModelProviderTask score$/in$/outContext
01Qwen: Qwen3.7 FlashQQwen5.00/5.0$0.030$0.1301M
02NVIDIA: Nemotron 3 Nano 30B A3BNNVIDIA5.00/5.0$0.050$0.200262K
03MiMo-V2.5XXiaomi5.00/5.0$0.140$0.2801.1M
04NVIDIA: Nemotron 3 SuperNNVIDIA5.00/5.0$0.085$0.4001M
05DeepSeek V3.2DDeepSeek5.00/5.0$0.269$0.400164K
06OpenAI: GPT-5.6 LunaOOpenAI5.00/5.0$0.100$0.6001.1M
07Inception: Mercury 2IInception5.00/5.0$0.250$0.750128K
08MiniMax: MiniMax M2.5MMinimax5.00/5.0$0.150$0.900205K
09DeepSeek V4 ProDDeepSeek5.00/5.0$0.435$0.8701.0M
10DeepSeek V3.1DDeepSeek5.00/5.0$0.250$0.950164K
11Qwen: Qwen3.6 35B A3BQQwen5.00/5.0$0.140$1.00262K
12Qwen: Qwen3.5-35B-A3BQQwen5.00/5.0$0.140$1.00262K
13Nex-N2-ProNNex AGI5.00/5.0$0.250$1.00262K
14MiniMax: MiniMax M2.7MMinimax5.00/5.0$0.250$1.00205K
15Qwen: Qwen3.6 FlashQQwen5.00/5.0$0.188$1.131M
16StepFun: Step 3.7 FlashSStepfun5.00/5.0$0.200$1.15262K
17MiniMax: MiniMax M3MMinimax5.00/5.0$0.300$1.201.0M
18Qwen: Qwen3.7 PlusQQwen5.00/5.0$0.320$1.281M
19Gemini 3.1 Flash Lite PreviewGGoogle5.00/5.0$0.250$1.501.0M
20GLM-4.7ZZhipu AI5.00/5.0$0.400$1.75205K
21Qwen: Qwen3.5 Plus 2026-04-20QQwen5.00/5.0$0.300$1.801M
22Qwen: Qwen3.6 PlusQQwen5.00/5.0$0.325$1.951M
23GPT-5 MiniOOpenAI5.00/5.0$0.250$2.00400K
24ByteDance Seed: Seed-2.0-LiteBBytedance-seed5.00/5.0$0.250$2.00262K
25ByteDance Seed: Seed 1.6BBytedance-seed5.00/5.0$0.250$2.00262K
26Qwen: Qwen3.6 27BQQwen5.00/5.0$0.300$2.00262K
27xAI: Grok Build 0.1XXAI5.00/5.0$1.00$2.00256K
28MoonshotAI: Kimi K2.6MMoonshotAI5.00/5.0$0.600$3.41262K
29Z.ai: GLM 5.2ZZhipu AI5.00/5.0$1.19$3.741.0M
30Thinking Machines: InklingTThinkingmachines5.00/5.0$1.00$4.051.0M
31Meta: Muse Spark 1.1MMeta5.00/5.0$1.25$4.251.0M
32o4 MiniOOpenAI5.00/5.0$1.10$4.40200K
33Qwen 3.7 MaxQQwen5.00/5.0$1.48$4.421M
34OpenAI: GPT-5.6 TerraOOpenAI5.00/5.0$1.00$6.001.1M
35Qwen: Qwen3.6 Max PreviewQQwen5.00/5.0$1.03$6.16262K
36Grok 4.5XXAI5.00/5.0$2.00$6.00500K
37o3OOpenAI5.00/5.0$2.00$8.00200K
38Gemini 3.5 FlashGGoogle5.00/5.0$1.50$9.001.0M
39GPT-5OOpenAI5.00/5.0$1.25$10.00400K
40Anthropic: Claude Sonnet 5AAnthropic5.00/5.0$2.00$10.001M
41Gemini 3.1 Pro PreviewGGoogle5.00/5.0$2.00$12.001.0M
42OpenAI: GPT-5.6 Terra ProOOpenAI5.00/5.0$2.50$15.001.1M
43Claude Opus 5AAnthropic5.00/5.0$5.00$25.001M
44Anthropic: Claude Opus 4.8AAnthropic5.00/5.0$5.00$25.001M
45OpenAI: GPT-5.6 SolOOpenAI5.00/5.0$5.00$30.001.1M
46Anthropic: Claude Opus 4.8 (Fast)AAnthropic5.00/5.0$10.00$50.001M
47Anthropic: Claude Fable 5AAnthropic5.00/5.0$10.00$50.001M
48Poolside: Laguna XS 2.1PPoolside4.67/5.0$0.060$0.120262K
49OpenAI: gpt-oss-120bOOpenAI4.67/5.0$0.037$0.170131K
50Qwen: Qwen3.5-9BQQwen4.67/5.0$0.100$0.150262K
51StepFun: Step 3.5 FlashSStepfun4.67/5.0$0.100$0.300262K
52Gemma 4 26B A4B GGoogle4.67/5.0$0.070$0.340262K
53Gemma 4 31BGGoogle4.67/5.0$0.100$0.340262K
54GPT-5 NanoOOpenAI4.67/5.0$0.050$0.400400K
55ByteDance Seed: Seed-2.0-MiniBBytedance-seed4.67/5.0$0.100$0.400262K
56inclusionAI: Ring-2.6-1TIInclusionai4.67/5.0$0.075$0.625262K
57inclusionAI: Ling-2.6-1TIInclusionai4.67/5.0$0.075$0.625262K
58Arcee AI: Trinity Large ThinkingAArcee-ai4.67/5.0$0.220$0.850262K
59MiMo-V2.5-ProXXiaomi4.67/5.0$0.435$0.8701.1M
60MiniMax: MiniMax M2MMinimax4.67/5.0$0.255$1.02205K
61Mistral Large 3 2512MMistral4.67/5.0$0.500$1.50262K
62R1 0528DDeepSeek4.67/5.0$0.500$2.15164K
63Gemini 3.5 Flash LiteGGoogle4.67/5.0$0.300$2.501.0M
64Gemini 3 Flash PreviewGGoogle4.67/5.0$0.500$3.001.0M
65KAT-Coder-Pro V2.5KKwaipilot4.67/5.0$0.740$2.96256K
66Kimi K2.7 CodeMMoonshot AI4.67/5.0$0.730$3.50262K
67NVIDIA: Nemotron 3 UltraNNVIDIA4.67/5.0$0.600$3.60512K
68OpenAI: GPT-5.6 Luna ProOOpenAI4.67/5.0$1.00$6.001.1M
69Gemini 3.6 FlashGGoogle4.67/5.0$1.50$7.501.0M
70Gemini 2.5 ProGGoogle4.67/5.0$1.25$10.001.0M
71GPT-5.2OOpenAI4.67/5.0$1.75$14.00400K
72GPT-5.4OOpenAI4.67/5.0$2.50$15.001.1M
73Claude Sonnet 4.6AAnthropic4.67/5.0$3.00$15.001M
74MoonshotAI: Kimi K3MMoonshotAI4.67/5.0$3.00$15.001.0M
75Grok 4XXAI4.67/5.0$3.00$15.00256K
76Grok 3XXAI4.67/5.0$3.00$15.00131K
77Claude Opus 4.7AAnthropic4.67/5.0$5.00$25.001M
78Claude Opus 4.6AAnthropic4.67/5.0$5.00$25.001M
79GPT-5.5OOpenAI4.67/5.0$5.00$30.001.1M
80OpenAI: GPT-5.6 Sol ProOOpenAI4.67/5.0$5.00$30.001.1M
81Claude Opus 5 (Fast)AAnthropic4.67/5.0$10.00$50.001M
82inclusionAI: Ling-2.6-flashIInclusionai4.33/5.0$0.010$0.030262K
83Qwen: Qwen3 30B A3B Instruct 2507QQwen4.33/5.0$0.048$0.193262K
84Poolside Laguna S 2.1PPoolside4.33/5.0$0.090$0.1801.0M
85ByteDance Seed: Seed 1.6 FlashBBytedance-seed4.33/5.0$0.075$0.300262K
86DeepSeek V4 FlashDDeepSeek4.33/5.0$0.140$0.2801.0M
87GLM-4.7 FlashZZhipu AI4.33/5.0$0.060$0.400203K
88Gemini 2.5 Flash LiteGGoogle4.33/5.0$0.100$0.4001.0M
89GPT-4.1 NanoOOpenAI4.33/5.0$0.100$0.4001.0M
90Grok 4.1 FastXXAI4.33/5.0$0.200$0.5002M
91Qwen: Qwen3 235B A22B Instruct 2507QQwen4.33/5.0$0.150$0.598262K
92DeepSeek V3.1 TerminusDDeepSeek4.33/5.0$0.270$1.00164K
93Kwaipilot: KAT-Coder-Pro V2KKwaipilot4.33/5.0$0.300$1.20262K
94MiniMax: MiniMax M2.1MMinimax4.33/5.0$0.300$1.20205K
95Grok Code Fast 1XXAI4.33/5.0$0.200$1.50256K
96Google: Gemini 3.1 Flash LiteGGoogle4.33/5.0$0.250$1.501.0M
97R1DDeepSeek4.33/5.0$0.700$2.50164K
98Grok 4.20XXAI4.33/5.0$1.25$2.502M
99Grok 4.3XXAI4.33/5.0$1.25$2.501M
100Mistral Medium 3.5MMistral4.33/5.0$1.50$7.50262K
101GPT-4.1OOpenAI4.33/5.0$2.00$8.001.0M
102GPT-5.1OOpenAI4.33/5.0$1.25$10.00400K
103OpenAI: gpt-oss-20bOOpenAI4.00/5.0$0.030$0.130131K
104Ministral 3 14B 2512MMistral4.00/5.0$0.200$0.200262K
105Xiaomi: MiMo-V2-FlashXXiaomi4.00/5.0$0.100$0.300262K
106KAT-Coder-Air V2.5KKwaipilot4.00/5.0$0.150$0.600256K
107Mistral Small 4MMistral4.00/5.0$0.150$0.600262K
108Llama 4 MaverickMMeta4.00/5.0$0.200$0.8001.0M
109Codestral 2508MMistral4.00/5.0$0.300$0.900256K
110GPT-5.4 NanoOOpenAI4.00/5.0$0.200$1.25400K
111GPT-4.1 MiniOOpenAI4.00/5.0$0.400$1.601.0M
112Devstral 2 2512MMistral4.00/5.0$0.400$2.00262K
113Mistral Medium 3.1MMistral4.00/5.0$0.400$2.00131K
114Gemini 2.5 FlashGGoogle4.00/5.0$0.300$2.501.0M
115GPT-5.4 MiniOOpenAI4.00/5.0$0.750$4.50400K
116Claude Haiku 4.5AAnthropic4.00/5.0$1.00$5.00200K
117Ministral 3 3B 2512MMistral3.67/5.0$0.100$0.100131K
118Mistral Small 3.2 24BMMistral3.67/5.0$0.075$0.200256K
119Qwen: Qwen3 Coder 30B A3B InstructQQwen3.67/5.0$0.070$0.280262K
120Llama 4 ScoutMMeta3.67/5.0$0.100$0.3001.3M
121Llama 3.3 70B InstructMMeta3.67/5.0$0.130$0.400131K
122Grok 3 MiniXXAI3.67/5.0$0.300$0.500131K
123MiniMax: MiniMax-01MMinimax3.67/5.0$0.200$1.101.0M
124MiniMax: MiniMax M2-herMMinimax3.67/5.0$0.300$1.2066K
125GPT-4oOOpenAI3.67/5.0$2.50$10.00128K
126IBM: Granite 4.1 8BIIbm-granite3.33/5.0$0.050$0.100131K
127Ministral 3 8B 2512MMistral3.33/5.0$0.150$0.150262K
128GPT-4o-miniOOpenAI3.00/5.0$0.150$0.600128K
129Mistral Small 3.1 24BMMistral3.00/5.0$0.351$0.555128K
130MiniMax: MiniMax M1MMinimax3.00/5.0$0.550$2.201M
131IBM: Granite 4.0 MicroIIbm-granite2.33/5.0$0.017$0.112131K

Pricing — top 5 for tabular data & spreadsheets

QQwen: Qwen3.7 Flash
$0.105/MTok
5.00/5.0
NNVIDIA: Nemotron 3 Nano 30B A3B
$0.163/MTok
5.00/5.0
XMiMo-V2.5
$0.245/MTok
5.00/5.0
NNVIDIA: Nemotron 3 Super
$0.321/MTok
5.00/5.0
DDeepSeek V3.2
$0.367/MTok
5.00/5.0
modelpicker.aipowered by live benchmark data

The best AI for tabular data & spreadsheets changes every month.

We'll email you when rankings shift, new models hit the top 5, or pricing cuts reshuffle the value leaders.

Get notified when models change
Price drops, new models, benchmark updates. One email per change, no spam.