DeepSeek, released May 29, 2025

DeepSeek R1 0528 Qwen3 8Bprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 32% confidence, 1 of 7 expected sources in

40.3

SI Score

Not ranked yet

Input, per 1M tokens: not yet reported
Output, per 1M tokens: not yet reported
Context window: 131K
Max output: 32K
Released: May 29, 2025

How this score is built

Coding —

Math 43.9

Preference —

Reasoning 9.3

How DeepSeek R1 0528 Qwen3 8B's SI Score is calculated
Pillar	Score	Weight	Adds
Math	43.9	33% of 15%	14.6
Reasoning	9.3	67% of 30%	6.2
Coding	Not measured yet, left out
Preference	Not measured yet, left out
Average of measured pillars	20.8
Evidence check	19.5 (2.0 of 6suites needed)
SI Score	40.3

Measured suites (2)

Related tasks and editions share one suite weight in each pillar, and one reliability-weighted breadth contribution across the model.

aime: 1.00 breadth; Math 43.9 × 0.50. 1 result ID: otis-mock-aime-2024-2025
gpqa: 1.00 breadth; Reasoning 9.3 × 0.50. 1 result ID: gpqa-diamond

Missing pillars are left out and the remaining weights are rescaled, so nothing counts as a zero. With fewer than 6 weighted suites, the average is pulled toward 50 until more results arrive. Ranking needs at least three measured pillars. Still to report for this model, and not counted against it: ARC Prize, Humanity’s Last Exam, Official model cards via models.dev, LiveBench, LMArena / Arena, Terminal-Bench. Full method

Method si-v5-suite-evidence-1, computed Oct 9, 2026, 18:16 UTC.

Around it on the leaderboard

Full leaderboard

Benchmark results

2 benchmarks, 2 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 9.3% 9.3

OTIS Mock AIME 2024–2025math 43.9% 43.9

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: MIT
Input modalities: text
First seen by SuperIndex: Oct 9, 2026
Coverage: 25% of expected source weight

Reported (1)

Epoch AI BenchmarkingOct 9, 2026

Awaiting (6)

ARC Prize13% of weight
Humanity’s Last Exam13% of weight
Official model cards via models.dev4% of weight
LiveBench13% of weight
LMArena / Arena25% of weight
Terminal-Bench6% of weight

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