Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is DeepSeek V4 Flash 0731?

124 SI-IQ · 90% interval 121–127
Rank 33 of 80 ranked models · Plausible rank range 19–44

DeepSeek V4 Flash 0731 is a model from DeepSeek, released on Jul 31, 2026. Its SI-IQ is 124 (90% interval 121–127), estimated from 8 benchmark results by 2 independent evaluators. Its strongest area is Reasoning and its weakest is Math.

Facts

Developer: DeepSeek
Released: Jul 31, 2026
Access: Open weights (restricted licence)
Benchmarks used: 8 results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
Chess Puzzles	Reasoning	32.0%	122	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles	Reasoning	34.0%	127	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4	Math	24.4%	123	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	57.5%	123	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	94.4%	122	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	91.0%	127	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	90.0%	130	OpenRouter	`deepseek/deepseek-v4-flash-20260731` DeepSeek · first-party provider (1 of 35 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	33.6%	113	Epoch AI	`deepseek-v4-flash-0731_max`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	77.7%	134	OpenRouter	`deepseek/deepseek-v4-flash-20260731` DeepSeek · first-party provider (1 of 35 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Models with similar SI-IQ

Model	SI-IQ
Claude Opus 4.6Anthropic	123	DeepSeek V4 Flash 0731 vs Claude Opus 4.6
Gemini 3.6 FlashGoogle DeepMind	125	DeepSeek V4 Flash 0731 vs Gemini 3.6 Flash
Gemini 3 FlashGoogle DeepMind	122	DeepSeek V4 Flash 0731 vs Gemini 3 Flash
Qwen3.7-MaxAlibaba	125	DeepSeek V4 Flash 0731 vs Qwen3.7-Max
GPT-5.2OpenAI	125	DeepSeek V4 Flash 0731 vs GPT-5.2

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..