Noometry

Model comparison

GPT-6.1 Sol vs Tulu 3 (Tülu 3) 70B

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 33.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Tulu 3 (Tülu 3) 70B Allen Institute for AI (Ai2)

33.0

Rank #251 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6.1 Sol and 4.4% for Tulu 3 (Tülu 3) 70B.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolTulu 3 (Tülu 3) 70B
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index65.633.0
Released2026-09-292024-11-21
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3414

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

Category by category

Coding GPT-6.1 Sol leads

GPT-6.1 Sol: 63.2 (#8), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Coding14871235
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Tulu 3 (Tülu 3) 70B: —

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
APEX-Agents60%—
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Hard Prompts14661220
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—
Epoch Capabilities Index166.09—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-2025100%4.4%
LMArena Math14641242
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
ProofBench99%—
MATH Level 5—42.7%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
GPQA Diamond95.4%46.3%
SimpleQA Verified73.9%—
LMArena Expert1502—

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Tulu 3 (Tülu 3) 70B: —

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Non-English14381236
LMArena Chinese14771249
LMArena Russian14551246

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Instruction Following14681233

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Longer Query14651224

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkGPT-6.1 SolTulu 3 (Tülu 3) 70B
LMArena Text14471256
LMArena Creative Writing14321231
LMArena Multi-Turn14491252

Frequently asked questions

Is GPT-6.1 Sol better than Tulu 3 (Tülu 3) 70B?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 33.0 on the Noometry Index.

Is GPT-6.1 Sol or Tulu 3 (Tülu 3) 70B better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 36.0 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper