Compare · ModelsLive · 2 picked · head to head

DeepSeek V3.2 Speciale vs Qwen3 30B A3B Thinking 2507

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

Winner summary

DeepSeek V3.2 Speciale wins 6 of 6 shared benchmarks. Leads in math · knowledge · language.

Category leads
math·DeepSeek V3.2 Specialeknowledge·DeepSeek V3.2 Specialelanguage·DeepSeek V3.2 Specialecoding·DeepSeek V3.2 Speciale

Head to head · from the data · data as of 2026-11-17

  • Benchmarks · DeepSeek V3.2 Speciale leads on 6 of 6 shared benchmarks (OpenCompass · AIME2025, OpenCompass · GPQA-Diamond, OpenCompass · HLE, OpenCompass · IFEval, 2 more), Qwen3 30B A3B Thinking 2507 on 0
  • Price · DeepSeek V3.2 Speciale input $0.40/M vs Qwen3 30B A3B Thinking 2507 $0.20/M, Qwen3 30B A3B Thinking 2507 is 50% cheaper (OpenRouter list price, as of 2026-11-17)
  • Context · DeepSeek V3.2 Speciale 164K tokens vs Qwen3 30B A3B Thinking 2507 82K tokens
  • Released · DeepSeek V3.2 Speciale Dec 1, 2025 vs Qwen3 30B A3B Thinking 2507 Aug 28, 2025 · 4 months apart
  • Open weights · DeepSeek V3.2 Speciale and Qwen3 30B A3B Thinking 2507 both have open weights
  • Price history · DeepSeek V3.2 Speciale OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17 · Qwen3 30B A3B Thinking 2507 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
DeepSeek V3.2 Speciale
#4 by perf·no signal
QUIET
Qwen3 30B A3B Thinking 2507
#34 by perf·#1 by attention
DESERVED
Best value
1.9x better value than Qwen3 30B A3B Thinking 2507
DeepSeek V3.2 Speciale
97.8 pts/$
$0.80/M
Qwen3 30B A3B Thinking 2507
50.9 pts/$
$1.30/M
Vendor risk
One or more vendors flagged
DeepSeek logo
DeepSeek
$3.4B·Tier 1
Higher risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Head to head
DeepSeek V3.2 SpecialeQwen3 30B A3B Thinking 2507
OpenCompass · AIME2025
DeepSeek V3.2 Speciale leads by +9.2
DeepSeek V3.2 Speciale
96.0
Qwen3 30B A3B Thinking 2507
86.8
OpenCompass · GPQA-Diamond
DeepSeek V3.2 Speciale leads by +16.6
DeepSeek V3.2 Speciale
86.7
Qwen3 30B A3B Thinking 2507
70.1
OpenCompass · HLE
DeepSeek V3.2 Speciale leads by +16.9
DeepSeek V3.2 Speciale
28.6
Qwen3 30B A3B Thinking 2507
11.7
OpenCompass · IFEval
DeepSeek V3.2 Speciale leads by +2.0
DeepSeek V3.2 Speciale
91.7
Qwen3 30B A3B Thinking 2507
89.7
OpenCompass · LiveCodeBenchV6
DeepSeek V3.2 Speciale leads by +21.5
DeepSeek V3.2 Speciale
80.9
Qwen3 30B A3B Thinking 2507
59.4
OpenCompass · MMLU-Pro
DeepSeek V3.2 Speciale leads by +6.0
DeepSeek V3.2 Speciale
85.5
Qwen3 30B A3B Thinking 2507
79.5
Full benchmark table
BenchmarkDeepSeek V3.2 SpecialeQwen3 30B A3B Thinking 2507
OpenCompass · AIME2025
96.086.8
OpenCompass · GPQA-Diamond
86.770.1
OpenCompass · HLE
28.611.7
OpenCompass · IFEval
91.789.7
OpenCompass · LiveCodeBenchV6
80.959.4
OpenCompass · MMLU-Pro
85.579.5
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
DeepSeek logoDeepSeek V3.2 Speciale$0.40$1.20164K tokens (~82 books)$6.00
Alibaba Qwen logoQwen3 30B A3B Thinking 2507$0.20$2.4082K tokens (~41 books)$7.50
DeepSeek V3.2 Speciale leads on 6 of 6 shared benchmarks (OpenCompass · AIME2025, OpenCompass · GPQA-Diamond, OpenCompass · HLE, OpenCompass · IFEval, 2 more), Qwen3 30B A3B Thinking 2507 on 0