qwen3-4b: benchmark scores, price and ranking

qwen3-4b from Alibaba ranks #394 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.9), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Alibaba
Type: Open-weight / local model
Open weights: Yes
Released: 2025-04-29 (source: epoch)
Cheapest API price: $0.080 in / $0.240 out per million tokens (via nebius, observed 2026-10-13T20:47Z)
Aggregate rank: #394 of 743 (score 47.9)

Across the 1 benchmark where at least ten models are scored, qwen3-4b is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.080 per million tokens, is lower than that of 85% of the 427 models with a listed price.

qwen3-4b benchmark results

qwen3-4b benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GPQA Diamond	52.3%	#181 of 275	Epoch AI Benchmarking Hub	2026-10-13

About qwen3-4b

qwen3-4b is an open-weight model that can run on your own hardware from Alibaba. It was released on 2025-04-29, according to Epoch AI. The cheapest API listing we track charges $0.080 per million input tokens and $0.240 per million output tokens, through nebius. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where qwen3-4b stands

On our aggregate score, qwen3-4b is #394 of 743 ranked models, around the middle of the table. Its score is 47.9; the scale is centred on 50, so it sits 2.1 points below the typical model. That beats 47% of the ranked field. Among the 74 ranked Alibaba models it is #40. The next one up is qwen3-coder-plus at 48.0. The next one down is qwen3-235b-a22b at 47.9.

qwen3-4b, benchmark by benchmark

qwen3-4b lands below the middle on GPQA Diamond: 52.3%, #181 of 275, with 65% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is grok-2-1212 at 53.8%. It covers expert-level science questions. The board median is 71.7%, so qwen3-4b is 19.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so qwen3-4b 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 Qwen3-Next-80B-A3B-Instruct ($0.090) and Qwen3-235B-A22B-Instruct-2507 ($0.090).

Release history

The Alibaba model released before it was Qwen3-32B on 2025-04-29, which scores 46.9. The next one was Qwen3-Coder-480B-A35B-Instruct on 2025-07-22, at 45.5.

Reading these numbers

The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 1 other reasoning-effort setting of this model, which redirect here. This page shows the highest. With 1 results the aggregate rank can move a lot when one new score arrives.

qwen3-4b is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

#391 Codex + GPT-6 Luna (48.0)
#392 Codestral-22B-v0.1-Q4_K_M (48.0)
#393 codestral:22b-v0.1-q8_0 (48.0)
#395 DeepSeek-R1-Distill-Qwen-32B (47.9)
#396 DeepSeek-V3.2 (Thinking; Fireworks) (47.9)
#397 qwen3-235b-a22b (47.9)