Model comparison

Qwen3-1.7B vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 26.6 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

Qwen3-1.7B

Alibaba (Qwen)

26.6

Rank #336 Reported

Solar Pro4

Upstage

42.1

Rank #121 Confirmed

Summary

The widest gap is in math, where Solar Pro4 leads 38.8 to 16.3.
Qwen3-1.7B has downloadable open weights; the other is API-only.

Side by side

Qwen3-1.7B and Solar Pro4 specifications
	Qwen3-1.7B	Solar Pro4
Provider	Alibaba (Qwen)	Upstage
Noometry Index	26.6	42.1
Released	2025-04-29	2026-08-06
Weights	Open	Proprietary
Context window	—	524K
Max output	—	131K
Input $ / M tokens	—	$0.30
Output $ / M tokens	—	$1.20
Results tracked	4	18

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Qwen3-1.7B: —, Solar Pro4: 40.1 (#149)

Coding benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
LMArena WebDev	—	1371
LMArena Coding	—	1437

Agentic & Tool Use Not comparable

Qwen3-1.7B: 24.7 (#115), Solar Pro4: —

Agentic & Tool Use benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
Berkeley Function Calling Leaderboard	28.4%	—

Reasoning Solar Pro4 leads

Qwen3-1.7B: 19.2 (#267), Solar Pro4: 28.5 (#104)

Reasoning benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
Chess Puzzles	0%	—
LMArena Hard Prompts	—	1399

Math Solar Pro4 leads

Qwen3-1.7B: 16.3 (#294), Solar Pro4: 38.8 (#128)

Math benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
OTIS Mock AIME 2024-2025	8.1%	—
LMArena Math	—	1416

Knowledge Solar Pro4 leads

Qwen3-1.7B: 19.6 (#278), Solar Pro4: 39.8 (#129)

Knowledge benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
GPQA Diamond	38%	—
LMArena Expert	—	1427

Multilingual Not comparable

Qwen3-1.7B: —, Solar Pro4: 48.7 (#139)

Multilingual benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
LMArena Non-English	—	1361
LMArena Chinese	—	1415
LMArena French	—	1397
LMArena German	—	1364
LMArena Japanese	—	1309
LMArena Korean	—	1382
LMArena Russian	—	1360
LMArena Spanish	—	1401

Instruction Following Not comparable

Qwen3-1.7B: —, Solar Pro4: 72.7 (#132)

Instruction Following benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
LMArena Instruction Following	—	1377

Long Context Not comparable

Qwen3-1.7B: —, Solar Pro4: 42.1 (#130)

Long Context benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
LMArena Longer Query	—	1381

Writing & Preference Not comparable

Qwen3-1.7B: —, Solar Pro4: 56.5 (#138)

Writing & Preference benchmarks
Benchmark	Qwen3-1.7B	Solar Pro4
LMArena Text	—	1386
LMArena Creative Writing	—	1316
LMArena Multi-Turn	—	1385

Frequently asked questions

Is Qwen3-1.7B better than Solar Pro4?