Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes

AGIEval

A human-centric exam benchmark for general knowledge and reasoning reported in DeepSeek-V4 base-model evaluations.

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on AGIEval — September 15, 2026

We mirror the published score view for AGIEval. DeepSeek V4 Pro Base leads the public snapshot at 83.1%, followed by DeepSeek V4 Flash Base (82.6%) and Soofi S 30B-A3B (66.9%). We do not use these results to rank models overall.

1Open weights

DeepSeek V4 Pro Base

DeepSeek

83.1%
Context 1M
2Open weights

DeepSeek V4 Flash Base

DeepSeek

82.6%
Context 1M
3Open weights

Soofi S 30B-A3B

Soofi Project

66.9%
Context 1M

3 modelsKnowledgeCurrentDisplay onlyUpdated September 15, 2026

Benchmark score table (3 models)

Score
1
DeepSeek V4 Pro BaseDeepSeek · Open weight
83.1%
2
DeepSeek V4 Flash BaseDeepSeek · Open weight
82.6%
3
Soofi S 30B-A3BSoofi Project · Open weight
66.9%

The published AGIEval snapshot places DeepSeek V4 Pro Base first at 83.1%. The third row is 16.2 points behind. The broader top-10 range is 16.2 points, so the table still separates the published systems.

3 models have been evaluated on AGIEval. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. AGIEval is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AGIEval

Year

2026

Tasks

General academic and professional exam questions

Format

Exact match

Difficulty

General knowledge

BenchLM stores AGIEval as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.

BenchLM freshness & provenance

Version

AGIEval 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does AGIEval measure?

A human-centric exam benchmark for general knowledge and reasoning reported in DeepSeek-V4 base-model evaluations.

Which model scores highest on AGIEval?

DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 83.1% on AGIEval.

How many models are evaluated on AGIEval?

3 AI models have been evaluated on AGIEval on BenchLM.

Last updated: September 15, 2026 · BenchLM version AGIEval 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.