DeepSeek V4.1 Flash 1017 vs GLM 5.2

DeepSeek against Z.AI. Prices, scores and speed below are live.

  • DeepSeek V4.1 Flash 1017 costs 75% less on blended price ($0.39 against $1.60 per 1M tokens, 3 input to 1 output).
  • GLM 5.2 scores higher on the Artificial Analysis Intelligence Index: 34 against 32.6.
  • On the 21 benchmarks both have scores on, DeepSeek V4.1 Flash 1017 leads on 18 and GLM 5.2 on 3.
  • Both read up to 1M tokens of context.
  • DeepSeek V4.1 Flash 1017 is newer: listed Oct 17, 2026, against Jun 16, 2026.

Side by side

DeepSeek V4.1 Flash 1017GLM 5.2
LabDeepSeekZ.AI
ListedOct 17, 2026Jun 16, 2026
Input per 1M tokens$0.23$0.93
Output per 1M tokens$0.90$3.63
Cached input per 1M$0.0045$0.21
Blended (3:1) per 1M$0.39$1.60
Context window1M1M
Max output393K944K
Knowledge cutoff--
Intelligence index32.634
Coding index-68.8
ReasoningYesYes
Reads imagesYesNo
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkDeepSeek V4.1 Flash 1017GLM 5.2
AIME99.4%Epoch AI28.9%Epoch AI
APEX-Agents69.8%Epoch AI45.2%Epoch AI
ARC-AGI-194.5%Epoch AI77%Epoch AI
ARC-AGI-278.1%Epoch AI22.8%Epoch AI
Artificial Analysis Intelligence Index32.6Artificial Analysis and OpenRouter34Artificial Analysis and OpenRouter
Chess Puzzles46%Epoch AI22%Epoch AI
Design Arena: 3D1332 EloDesign Arena1253 EloDesign Arena
Design Arena: ASCII Art1222 EloDesign Arena1173 EloDesign Arena
Design Arena: Code1281 EloDesign Arena1269 EloDesign Arena
Design Arena: Data Viz1271 EloDesign Arena1279 EloDesign Arena
Design Arena: Game Dev1248 EloDesign Arena1244 EloDesign Arena
Design Arena: SVG1235 EloDesign Arena1189 EloDesign Arena
Design Arena: UI Component1274 EloDesign Arena1279 EloDesign Arena
Design Arena: Website1289 EloDesign Arena1272 EloDesign Arena
FrontierMath Tier 4 (v2)46.3%Epoch AI29.3%Epoch AI
FrontierMath Tiers 1-3 (v2)71.2%Epoch AI42.5%Epoch AI
GPQA Diamond90.1%Artificial Analysis and OpenRouter85.1%Artificial Analysis and OpenRouter
Mystery Game Puzzles49%Epoch AI15%Epoch AI
SciCode55.9%Epoch AI51.2%Epoch AI
SimpleQA Verified42.5%Epoch AI34.2%Epoch AI
tau-bench (Airline)73.3%Artificial Analysis and OpenRouter70.6%Artificial Analysis and OpenRouter

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See DeepSeek models, Z.AI models, every LLM's price and our sources.