qwen2.5-7b-instruct: benchmark scores, price and ranking

qwen2.5-7b-instruct from Alibaba ranks #735 of 743 LLMs on the LLMs Tiger aggregate benchmark score (39.9), based on 6 benchmark results captured up to 2026-10-13.

Organisation: Alibaba
Type: Open-weight / local model
Open weights: Yes
Released: 2024-09-19 (source: epoch)
Cheapest API price: $0.040 in / $0.100 out per million tokens (via deepinfra, observed 2026-10-13T20:47Z)
Aggregate rank: #735 of 743 (score 39.9)

Relative to other models, qwen2.5-7b-instruct is strongest on GPQA Diamond (#234 of 275) and weakest on Chess Puzzles (#121 of 122).

Across the 6 benchmarks where at least ten models are scored, qwen2.5-7b-instruct is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.040 per million tokens, is lower than that of 94% of the 427 models with a listed price.

qwen2.5-7b-instruct benchmark results

qwen2.5-7b-instruct benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GPQA Diamond	35.5%	#234 of 275	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	2.5%	#171 of 189	Epoch AI Benchmarking Hub	2026-10-13
BALROG	7.8%	#32 of 34	Epoch AI Benchmarking Hub	2026-10-13
LMCA	6.4%	#102 of 108	Epoch AI Benchmarking Hub	2026-10-13
DTBench	47.7%	#138 of 146	Epoch AI Benchmarking Hub	2026-10-13
Chess Puzzles	0.0%	#121 of 122	Epoch AI Benchmarking Hub	2026-10-13

About qwen2.5-7b-instruct

qwen2.5-7b-instruct is an open-weight model that can run on your own hardware from Alibaba. It was released on 2024-09-19, according to Epoch AI. The cheapest API listing we track charges $0.040 per million input tokens and $0.100 per million output tokens, through deepinfra. We hold 6 benchmark results for it across 3 areas, and none is in the top tenth of its board.

Where qwen2.5-7b-instruct stands

On our aggregate score, qwen2.5-7b-instruct is #735 of 743 ranked models, in the lower half. Its score is 39.9; the scale is centred on 50, so it sits 10.1 points below the typical model. That beats 1% of the ranked field. Among the 74 ranked Alibaba models it is #74. The next one up is qwen2.5-72b-instruct at 42.2.

qwen2.5-7b-instruct, benchmark by benchmark

GPQA Diamond is a weak spot. qwen2.5-7b-instruct scores 35.5%, #234 of 275, behind 85% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so qwen2.5-7b-instruct is 36.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

OTIS Mock AIME is a weak spot. qwen2.5-7b-instruct scores 2.5%, #171 of 189, behind 90% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so qwen2.5-7b-instruct is 55.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

BALROG is a weak spot. qwen2.5-7b-instruct scores 7.8%, #32 of 34, behind 91% of the models measured. The leader, GPT-6 Astra (max), reaches 68.3%. It covers long-horizon game-playing agents. The board median is 27.6%, so qwen2.5-7b-instruct is 19.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

LMCA is a weak spot. qwen2.5-7b-instruct scores 6.4%, #102 of 108, behind 94% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so qwen2.5-7b-instruct is 22.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

DTBench is a weak spot. qwen2.5-7b-instruct scores 47.7%, #138 of 146, behind 94% of the models measured. The leader, Claude Opus 5.5 (max), reaches 98.9%. It covers dynamic tool-use benchmark. The board median is 68.8%, so qwen2.5-7b-instruct is 21.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Chess Puzzles is a weak spot. qwen2.5-7b-instruct scores 0.0%, #121 of 122, behind 98% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so qwen2.5-7b-instruct is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 12% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#234 of 275) and its weakest is OTIS Mock AIME (#171 of 189). Agents and tool use: weak, ahead of 6% of the field on average across 2 benchmarks. Its best board here is BALROG (#32 of 34) and its weakest is DTBench (#138 of 146). General knowledge and chat: weak, ahead of 3% of the field on average across 2 benchmarks. Its best board here is LMCA (#102 of 108) and its weakest is Chess Puzzles (#121 of 122).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so qwen2.5-7b-instruct costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Llama-4-Scout-17B-16E-Instruct ($0.050) and gemma-3-4b-it ($0.050).

Release history

The Alibaba model released before it was Qwen2.5-7B on 2024-09-19, which scores 46.5. The next one was qwen-turbo-2024-11-01 on 2024-11-01, at 44.5.

Reading these numbers

The 6 scores on this page come from 1 source: Epoch AI Benchmarking Hub (6). No official leaderboard supplied any of them, so treat them as third-party measurements. With 6 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#732 claude-2.1 (40.6)
#733 Llama-4-Scout-17B-16E-Instruct (40.1)
#734 gemma-3-4b-it (39.9)
#736 claude-3-haiku-20240307 (39.9)
#737 gemma-3-27b-it (39.7)
#738 Meta-Llama-3-8B-Instruct (39.4)