Skip to content

DEV Community

Model Comparison Real Tests Series' Articles

Back to Jemmmm's Series

Cover image for GLM-5.2 と Claude Fable 5 を実測比較：出力予算、reasoning_tokens、そして 0.8 価格係数

Jemmmm

Jul 6

GLM-5.2 と Claude Fable 5 を実測比較：出力予算、reasoning_tokens、そして 0.8 価格係数

#ai #api #llm #benchmark

3 min read

Cover image for GLM-5.2 vs Claude Fable 5: ngân sách đầu ra, reasoning_tokens và mức discount 0.8

Jemmmm

Jul 6

GLM-5.2 vs Claude Fable 5: ngân sách đầu ra, reasoning_tokens và mức discount 0.8

#ai #api #llm #benchmark

4 min read

Cover image for Kimi K3 vs Claude Fable 5: Verification Depth or Faster Delivery?

Jemmmm

Jul 17

Kimi K3 vs Claude Fable 5: Verification Depth or Faster Delivery?

#ai #api #llm #benchmark

3 min read

Cover image for Kimi K3 против Claude Fable 5: точность проверки, обрезка кода и задержка API

Jemmmm

Jul 17

Kimi K3 против Claude Fable 5: точность проверки, обрезка кода и задержка API

#ai #api #llm #benchmark

2 min read

Cover image for Kimi K3 face à Claude Fable 5 : rigueur du raisonnement ou rapidité de livraison ?

Jemmmm

Jul 17

Kimi K3 face à Claude Fable 5 : rigueur du raisonnement ou rapidité de livraison ?

#ai #api #llm #benchmark

4 min read

Cover image for Kimi K3와 Claude Fable 5 실측: 수학 검증, 코드 완결성, 응답 속도의 차이

Jemmmm

Jul 17

Kimi K3와 Claude Fable 5 실측: 수학 검증, 코드 완결성, 응답 속도의 차이

#ai #api #llm #benchmark

2 min read

Cover image for Kimi K3 vs GPT-5.6-SOL: Stress Tests in Math, Physics, and Programming

Jemmmm

Jul 18

Kimi K3 vs GPT-5.6-SOL: Stress Tests in Math, Physics, and Programming

#ai #api #llm #benchmark

7 min read

Cover image for Kimi K3 против GPT-5.6-SOL: жёсткое сравнение на математике, физике и программировании

Jemmmm

Jul 18

Kimi K3 против GPT-5.6-SOL: жёсткое сравнение на математике, физике и программировании

#ai #api #llm #benchmark

2 min read

Cover image for Kimi K3 face à GPT-5.6-SOL : test réel sur des exercices difficiles en maths, physique et programmation

Jemmmm

Jul 18

Kimi K3 face à GPT-5.6-SOL : test réel sur des exercices difficiles en maths, physique et programmation

#ai #api #llm #benchmark

9 min read

Cover image for Kimi K3 vs GPT-5.6-SOL: 수학·물리·프로그래밍 고난도 실측 비교

Jemmmm

Jul 18

Kimi K3 vs GPT-5.6-SOL: 수학·물리·프로그래밍 고난도 실측 비교

#ai #api #llm #benchmark

2 min read

Cover image for Claude Opus 5 vs Claude Fable 5：実 API での 7 タスク検証と本番ルーティングの提案

Jemmmm

Jul 26

Claude Opus 5 vs Claude Fable 5：実 API での 7 タスク検証と本番ルーティングの提案

#ai #api #llm #benchmark

4 min read

Cover image for Claude Opus 5 vs Claude Fable 5: 7 реальных API-тестов и рекомендации по production-маршрутизации

Jemmmm

Jul 26

Claude Opus 5 vs Claude Fable 5: 7 реальных API-тестов и рекомендации по production-маршрутизации

#ai #api #llm #benchmark

4 min read

Cover image for Claude Opus 5 vs GPT-5.6-SOL: Core Accuracy Ties at 10/10 in a Reproducible Model Test

Jemmmm

Jul 30

Claude Opus 5 vs GPT-5.6-SOL: Core Accuracy Ties at 10/10 in a Reproducible Model Test

#ai #api #llm #benchmark

11 min read

Cover image for Claude Opus 5とGPT-5.6-SOLを10問で検証：正解率はともに10/10、完遂率と形式遵守には差

Jemmmm

Jul 30

Claude Opus 5とGPT-5.6-SOLを10問で検証：正解率はともに10/10、完遂率と形式遵守には差

#ai #api #llm #benchmark

4 min read

Cover image for Claude Opus 5 và GPT-5.6-SOL: kiểm thử 10 bài về độ chính xác, kết quả cốt lõi hòa 10/10

Jemmmm

Jul 30

Claude Opus 5 và GPT-5.6-SOL: kiểm thử 10 bài về độ chính xác, kết quả cốt lõi hòa 10/10

#ai #api #llm #benchmark

23 min read

Cover image for Claude Opus 5 против GPT-5.6 Luna: 18 проверяемых задач без рейтинга скорости

Jemmmm

Jul 30

Claude Opus 5 против GPT-5.6 Luna: 18 проверяемых задач без рейтинга скорости

#ai #api #llm #benchmark

1 min read

Cover image for Claude Opus 5 và GPT-5.6 Luna: 18 bài kiểm chứng, không xếp hạng theo tốc độ

Jemmmm

Jul 30

Claude Opus 5 và GPT-5.6 Luna: 18 bài kiểm chứng, không xếp hạng theo tốc độ

#ai #api #llm #benchmark

6 min read