VECTOR WIREAI INTELLIGENCE
PKT
Refresh Models Deals Regulatory Sources

Questions this page answers

Which is better, DeepSeek-R1 or Qwen3.5 122B A10B?
Across 33 shared benchmarks, DeepSeek-R1 scores higher on 3 and Qwen3.5 122B A10B on 30. The widest gap is τ²-Bench Telecom (AA run), where Qwen3.5 122B A10B scores 93.6 against 11.4. Tracked API pricing per million tokens: DeepSeek-R1 $1.35 in / $3.00 out, Qwen3.5 122B A10B $0.40 in / $3.20 out.

DeepSeek-R1 vs Qwen3.5 122B A10B

Across 33 shared benchmarks, DeepSeek-R1 scores higher on 3 and Qwen3.5 122B A10B on 30. The widest gap is τ²-Bench Telecom (AA run), where Qwen3.5 122B A10B scores 93.6 against 11.4. Tracked API pricing per million tokens: DeepSeek-R1 $1.35 in / $3.00 out, Qwen3.5 122B A10B $0.40 in / $3.20 out.

DeepSeekvsAlibaba33 shared benchmarks330 head-to-head
BenchmarkDeepSeek-R1Qwen3.5 122B A10B
AA Agentic Index3.121.3
AA Intelligence18.632.8
AA-LCR5670.3
AA-Omniscience-31.3-41.5
Artificial Analysis Coding Index24.645.7
browsecomp8.963.8
browsecomp_zh35.769.9
C-Eval91.891.9
critpt0.60.9
gdpval1.524.3
GPQA Diamond8186.6
HLE17.747.5
HMMT 202579.490.3
IFBench3976.1
ifeval83.393.4
longbench_v258.360.2
mmlu_prox75.582.2
mmlu_redux93.494
MMLU-Pro8586.7
multichallenge4561.5
OmniScience Accuracy30.724.4
OmniScience Non-Hallucination10.512.9
scicode35.742
SWE-bench Verified57.672
TauBench V3 - Banking6.415.3
Terminal-Bench 2.119.147.6
Terminal-Bench Hard6.131.1
vectara_answer_rate9799.8
vectara_avg_summary_length93.586.4
vectara_factual_consistency88.788.8
vectara_hallucination_rate11.311.2
τ²-Bench Telecom (AA run)11.493.6
τ³-Bench6.413.6

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.