Noometry

Model comparison

Grok 4.7 vs Qwen3.6 35B-A3B

Grok 4.7 is the stronger model overall, scoring 53.1 to 37.6 on the Noometry Index. Qwen3.6 35B-A3B costs 5.4× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

Last verified . 11 shared benchmarks.

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Qwen3.6 35B-A3B Alibaba (Qwen)

37.6

Rank #201 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Grok 4.7 scores higher in 5 categories and Qwen3.6 35B-A3B in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 28.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 76.8% for Grok 4.7 and 41.6% for Qwen3.6 35B-A3B.
  • Qwen3.6 35B-A3B is cheaper at $0.25 / $1.49 per million input/output tokens, against $2 / $6 for Grok 4.7.
  • Grok 4.7 accepts more context: 500K tokens versus 262K.
  • Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok 4.7Qwen3.6 35B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index53.137.6
Released2026-09-212026-04-01
WeightsProprietaryOpen
Context window500K262K
Max output500K66K
Input $ / M tokens$2$0.25
Output $ / M tokens$6$1.49
Results tracked3914

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

Category by category

Coding Grok 4.7 leads

Grok 4.7: 58.0 (#18), Qwen3.6 35B-A3B: 37.2 (#196)

BenchmarkGrok 4.7Qwen3.6 35B-A3B
SciCode57.8%35.8%
FrontierCode47.6%—
CursorBench46.3%—
LMArena WebDev1639—
FrontierSWE29.5%—
WeirdML—34.5%
LMArena Coding1427—

Agentic & Tool Use Grok 4.7 leads

Grok 4.7: 36.7 (#37), Qwen3.6 35B-A3B: 22.1 (#134)

BenchmarkGrok 4.7Qwen3.6 35B-A3B
Terminal-Bench—23%
APEX-Agents54.6%—
GDP.pdf22.8%—
Vending-Bench 210,537—

Reasoning Grok 4.7 leads

Grok 4.7: 49.1 (#40), Qwen3.6 35B-A3B: 28.0 (#109)

BenchmarkGrok 4.7Qwen3.6 35B-A3B
NYT Connections (extended)76.8%41.6%
CritPt18%0.3%
Chess Puzzles38%26%
Mystery Game Puzzles29%22%
DTBench96%73.9%
LMCA49.4%29.7%
Epoch Capabilities Index153.53143.93
LMArena Hard Prompts1413—
Surface Evolver Bench—44.4%

Math Grok 4.7 leads

Grok 4.7: 57.8 (#39), Qwen3.6 35B-A3B: 38.9 (#121)

BenchmarkGrok 4.7Qwen3.6 35B-A3B
FrontierMath (Tiers 1-3)53%20.4%
OTIS Mock AIME 2024-202598.1%86.7%
FrontierMath Tier 417.1%—
ProofBench34%—
LMArena Math1407—

Knowledge Grok 4.7 leads

Grok 4.7: 62.8 (#22), Qwen3.6 35B-A3B: 51.3 (#68)

BenchmarkGrok 4.7Qwen3.6 35B-A3B
GPQA Diamond92.7%84.8%
SimpleQA Verified56%—
LMArena Expert1422—

Multimodal Not comparable

Grok 4.7: 35.5 (#87), Qwen3.6 35B-A3B: —

BenchmarkGrok 4.7Qwen3.6 35B-A3B
LMArena Vision1228—
Blueprint-Bench 232.5%—
Furniture Assembly20.8%—

Multilingual Not comparable

Grok 4.7: 50.8 (#116), Qwen3.6 35B-A3B: —

BenchmarkGrok 4.7Qwen3.6 35B-A3B
LMArena Non-English1389—
LMArena Chinese1455—
LMArena French1455—
LMArena Russian1397—
LMArena Spanish1400—

Instruction Following Not comparable

Grok 4.7: 74.1 (#105), Qwen3.6 35B-A3B: —

BenchmarkGrok 4.7Qwen3.6 35B-A3B
LMArena Instruction Following1404—

Long Context Not comparable

Grok 4.7: 43.1 (#104), Qwen3.6 35B-A3B: —

BenchmarkGrok 4.7Qwen3.6 35B-A3B
LMArena Longer Query1413—

Writing & Preference Not comparable

Grok 4.7: 70.0 (#24), Qwen3.6 35B-A3B: —

BenchmarkGrok 4.7Qwen3.6 35B-A3B
LMArena Text1399—
LMArena Creative Writing1391—
EQ-Bench Creative Writing2007—
LMArena Multi-Turn1393—

Frequently asked questions

Is Grok 4.7 better than Qwen3.6 35B-A3B?

Grok 4.7 is the stronger model overall, scoring 53.1 to 37.6 on the Noometry Index. Qwen3.6 35B-A3B costs 5.4× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

Which is cheaper, Grok 4.7 or Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $1.49 per million output tokens; Grok 4.7 lists at $2 and $6.

Is Grok 4.7 or Qwen3.6 35B-A3B better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 37.2 in the Noometry coding category.

Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 262K.

How many benchmarks do Grok 4.7 and Qwen3.6 35B-A3B share?

11 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Qwen3.6 35B-A3B has 14.

Related comparisons

Go deeper