DeepSeek Chat V2.5: benchmark scores, price and ranking

DeepSeek Chat V2.5 from DeepSeek ranks #528 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.3), based on 2 benchmark results captured up to 2026-10-13.

Organisation: DeepSeek
Type: Open-weight / local model
Open weights: Yes
Released: 2024-09-05 (source: curated)
Aggregate rank: #528 of 743 (score 46.3)

Across the 2 benchmarks where at least ten models are scored, DeepSeek Chat V2.5 is in the top 10% on 0 and in the top half on 0.

DeepSeek Chat V2.5 benchmark results

DeepSeek Chat V2.5 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Aider Polyglot	17.8%	#40 of 49	Aider polyglot leaderboard	2026-10-13
Aider Refactoring	31.5%	#12 of 12	Aider Aider Refactoring leaderboard	2026-10-13

About DeepSeek Chat V2.5

DeepSeek Chat V2.5 is an open-weight model that can run on your own hardware from DeepSeek. It was released on 2024-09-05, according to the developer's announcement. No API price is listed for it yet. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where DeepSeek Chat V2.5 stands

On our aggregate score, DeepSeek Chat V2.5 is #528 of 743 ranked models, in the lower half. Its score is 46.3; the scale is centred on 50, so it sits 3.7 points below the typical model. That beats 29% of the ranked field. Among the 33 ranked DeepSeek models it is #27. The next one up is deepseek-chat at 46.5. The next one down is DeepSeek-V3 at 45.1.

DeepSeek Chat V2.5, benchmark by benchmark

Aider Polyglot is a weak spot. DeepSeek Chat V2.5 scores 17.8%, #40 of 49, behind 80% of the models measured. The leader, gemini-2.5-pro-preview-06-05, reaches 83.1%. It covers edits across 6 languages (225 exercises). The board median is 44.9%, so DeepSeek Chat V2.5 is 27.1 points below it. Source: Aider polyglot leaderboard, captured 2026-10-13.

Aider Refactoring is a weak spot. DeepSeek Chat V2.5 scores 31.5%, #12 of 12, behind 92% of the models measured. The leader, Claude 3.5-Sonnet-20241022, reaches 92.1%. It covers Aider official benchmark. The board median is 50.0%, so DeepSeek Chat V2.5 is 18.5 points below it. Source: Aider Aider Refactoring leaderboard, captured 2026-10-13.

Strengths and weaknesses

DeepSeek Chat V2.5 has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Release history

The DeepSeek model released before it was deepseek-llm-67b-chat on 2023-11-29, which scores 42.8. The next one was DeepSeek Chat V3 (prev) on 2024-12-26, at 50.5.

Reading these numbers

The 2 scores on this page come from 2 sources: Aider polyglot leaderboard (1), Aider Aider Refactoring leaderboard (1). 2 of them come from an official leaderboard and 0 from datasets or third-party runs. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#525 ollama/mistral-small (46.4)
#526 mistral-small-3.2-2506 (46.4)
#527 Phi-3-mini-128k-instruct (46.3)
#529 qwen1.5-110b-chat (46.3)
#530 Qwen2.5-3B (46.3)
#531 GPT-5.4 mini (xhigh) (46.3)