Noometry

Model comparison

Claude Sonnet 4.6 vs InternVL2-40B

Claude Sonnet 4.6 has enough public results to be ranked (#42); InternVL2-40B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

InternVL2-40B Shanghai AI Lab

36.0

Unranked Sparse

Summary

  • The widest gap is in multimodal, where Claude Sonnet 4.6 leads 38.0 to 33.0.
  • InternVL2-40B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6InternVL2-40B
ProviderAnthropicShanghai AI Lab
Noometry Index50.136.0
Released2026-02-172024-07-08
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked571

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

Category by category

Coding Not comparable

Claude Sonnet 4.6: 46.0 (#62), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1521—
SciCode46.8%—
WeirdML66.1%—
LMArena Coding1504—
ALE-Bench1,327—

Agentic & Tool Use Not comparable

Claude Sonnet 4.6: 39.1 (#26), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Not comparable

Claude Sonnet 4.6: 46.1 (#40), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
ARC-AGI-260.4%—
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
LMArena Hard Prompts1485—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
Epoch Capabilities Index152.25—
ForecastBench62—

Math Not comparable

Claude Sonnet 4.6: 51.9 (#41), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
LMArena Math1463—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Not comparable

Claude Sonnet 4.6: 51.6 (#60), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
GPQA Diamond87.4%—
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—
LMArena Expert1500—

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#61), InternVL2-40B: 33.0

BenchmarkClaude Sonnet 4.6InternVL2-40B
LMArena Vision1283—
Video-MME—61.2%
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Not comparable

Claude Sonnet 4.6: 54.6 (#39), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
LMArena Non-English1440—
LMArena Chinese1491—
LMArena French1465—
LMArena German1428—
LMArena Japanese1419—
LMArena Korean1411—
LMArena Russian1440—
LMArena Spanish1465—

Instruction Following Not comparable

Claude Sonnet 4.6: 77.6 (#23), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
LMArena Instruction Following1476—

Long Context Not comparable

Claude Sonnet 4.6: 45.3 (#40), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
LMArena Longer Query1479—

Writing & Preference Not comparable

Claude Sonnet 4.6: 70.4 (#22), InternVL2-40B: —

BenchmarkClaude Sonnet 4.6InternVL2-40B
LMArena Text1458—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1810—
EQ-Bench 41207—
LMArena Multi-Turn1464—

Frequently asked questions

Is Claude Sonnet 4.6 better than InternVL2-40B?

Claude Sonnet 4.6 has enough public results to be ranked (#42); InternVL2-40B does not yet, so treat this comparison as directional.

How many benchmarks do Claude Sonnet 4.6 and InternVL2-40B share?

0 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and InternVL2-40B has 1.

Related comparisons

Go deeper