Compare · ModelsLive · 3 picked · head to head

Qwen3.7 Max vs DeepSeek V4 Pro vs Kimi K2.7 Code

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

Qwen3.7 Max wins 12 of 17 shared benchmarks. Leads in speed · language · math.

Category leads
speed·Qwen3.7 Maxcoding·Kimi K2.7 Codereasoning·DeepSeek V4 Prolanguage·Qwen3.7 Maxmath·Qwen3.7 Maxknowledge·Qwen3.7 Max
Hype vs Reality
Qwen3.7 Max
#28 by perf·no signal
QUIET
DeepSeek V4 Pro
#13 by perf·no signal
QUIET
Kimi K2.7 Code
#42 by perf·no signal
QUIET
Best value
3.3x better value than Kimi K2.7 Code
Qwen3.7 Max
27.2 pts/$
$2.50/M
DeepSeek V4 Pro
112.8 pts/$
$0.65/M
Kimi K2.7 Code
34.3 pts/$
$1.84/M
Vendor risk
One or more vendors flagged
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
DeepSeek logo
DeepSeek
$3.4B·Tier 1
Higher risk
moonshotai logo
moonshotai
private · undisclosed
Unknown
Head to head
Qwen3.7 MaxDeepSeek V4 ProKimi K2.7 Code
Artificial Analysis · Agentic Index
DeepSeek V4 Pro leads by +5.8
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
Qwen3.7 Max
30.6
DeepSeek V4 Pro
36.4
Kimi K2.7 Code
29.6
Artificial Analysis · Coding Index
Qwen3.7 Max leads by +5.2
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
Qwen3.7 Max
66.0
DeepSeek V4 Pro
59.4
Kimi K2.7 Code
60.8
Artificial Analysis · Quality Index
Qwen3.7 Max leads by +1.7
Qwen3.7 Max
46.0
DeepSeek V4 Pro
44.3
Kimi K2.7 Code
42.0
LiveBench · Agentic Coding
Kimi K2.7 Code leads by +13.3
Qwen3.7 Max
51.7
DeepSeek V4 Pro
56.7
Kimi K2.7 Code
70.0
LiveBench · Coding
Qwen3.7 Max leads by +0.3
Qwen3.7 Max
74.2
DeepSeek V4 Pro
70.0
Kimi K2.7 Code
74.0
LiveBench · Data Analysis
DeepSeek V4 Pro leads by +2.8
Qwen3.7 Max
71.8
DeepSeek V4 Pro
74.5
Kimi K2.7 Code
62.7
LiveBench · If
Qwen3.7 Max leads by +11.7
Qwen3.7 Max
74.0
DeepSeek V4 Pro
62.4
Kimi K2.7 Code
56.3
LiveBench · Language
Qwen3.7 Max leads by +1.6
Qwen3.7 Max
79.7
DeepSeek V4 Pro
78.1
Kimi K2.7 Code
77.9
LiveBench · Mathematics
DeepSeek V4 Pro leads by +5.4
Qwen3.7 Max
85.3
DeepSeek V4 Pro
90.7
Kimi K2.7 Code
79.6
LiveBench · Overall
Qwen3.7 Max leads by +0.7
Qwen3.7 Max
74.3
DeepSeek V4 Pro
73.6
Kimi K2.7 Code
71.9
LiveBench · Reasoning
Qwen3.7 Max leads by +0.5
Qwen3.7 Max
83.3
DeepSeek V4 Pro
82.7
Kimi K2.7 Code
82.8
Chess Puzzles
Qwen3.7 Max leads by +1.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Qwen3.7 Max
22.0
Kimi K2.7 Code
21.0
FrontierMath-Tier-4-v2-Private
Qwen3.7 Max leads by +21.9
Qwen3.7 Max
34.1
Kimi K2.7 Code
12.2
FrontierMath-Tiers-1-3-v2-Private
Qwen3.7 Max leads by +10.5
Qwen3.7 Max
64.6
Kimi K2.7 Code
54.0
GPQA diamond
Qwen3.7 Max leads by +2.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen3.7 Max
88.8
Kimi K2.7 Code
86.0
OTIS Mock AIME 2024-2025
Kimi K2.7 Code leads by +1.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen3.7 Max
95.0
Kimi K2.7 Code
96.4
SimpleQA Verified
Qwen3.7 Max leads by +19.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Qwen3.7 Max
58.5
Kimi K2.7 Code
39.2
Full benchmark table
BenchmarkQwen3.7 MaxDeepSeek V4 ProKimi K2.7 Code
Artificial Analysis · Agentic Index
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
30.636.429.6
Artificial Analysis · Coding Index
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
66.059.460.8
Artificial Analysis · Quality Index
46.044.342.0
LiveBench · Agentic Coding
51.756.770.0
LiveBench · Coding
74.270.074.0
LiveBench · Data Analysis
71.874.562.7
LiveBench · If
74.062.456.3
LiveBench · Language
79.778.177.9
LiveBench · Mathematics
85.390.779.6
LiveBench · Overall
74.373.671.9
LiveBench · Reasoning
83.382.782.8
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
22.021.0
FrontierMath-Tier-4-v2-Private
34.112.2
FrontierMath-Tiers-1-3-v2-Private
64.654.0
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
88.886.0
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
95.096.4
SimpleQA Verified
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
58.539.2
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Alibaba Qwen logoQwen3.7 Max$1.25$3.751.0M tokens (~500 books)$18.75
DeepSeek logoDeepSeek V4 Pro$0.43$0.871.0M tokens (~524 books)$5.44
moonshotai logoKimi K2.7 Code$0.61$3.07262K tokens (~131 books)$12.26