DeepSeek, released Dec 26, 2024

DeepSeek-V3price, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 93% confidence, 2 of 4 expected sources in

54.1

SI Score

#93 of 142 ranked models

Input, per 1M tokens: $0.27
Output, per 1M tokens: $1.10
Context window: 131K
Max output: 8.2K
Released: Dec 26, 2024

How the score breaks down

Coding —

Math 48.5

Preference 66.0

Reasoning 56.5

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

91 Gemini 3 Flash Preview 54.8
92 Grok 4.3 54.6
93 DeepSeek-V3 54.1
94 Claude Sonnet 4.5 53.9
95 Inkling Small 53.6

Full leaderboard

Benchmark results

4 benchmarks, 4 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

GPQA Diamondreasoning 56.5% 56.5

MATH Level 5math 64.9% 64.9

OTIS Mock AIME 2024–2025math 15.8% 15.8

LMArena Textpreference 1332.5 elo 66.0

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: Yes
License: DeepSeek Model License
Input modalities: text
First seen by SuperIndex: Oct 8, 2026
Coverage: 75% of expected source weight

Reported (2)

Epoch AI BenchmarkingOct 8, 2026
LMArena / ArenaOct 8, 2026

Awaiting (2)

Official model cards via models.dev7% of weight
LiveBench19% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.