Noometry

Model comparison

GPT-6.1 Sol vs Phi-4 Mini

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.9 on the Noometry Index. Phi-4 Mini costs 30× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

Last verified . 2 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Phi-4 Mini Microsoft

30.9

Rank #283 Reported

Summary

  • They share 2 benchmarks with published results for both. GPT-6.1 Sol scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 22.4.
  • The biggest single-benchmark swing is SciCode: 55.8% for GPT-6.1 Sol and 10.8% for Phi-4 Mini.
  • Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
  • GPT-6.1 Sol accepts more context: 1.05M tokens versus 128K.
  • Phi-4 Mini has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolPhi-4 Mini
ProviderOpenAIMicrosoft
Noometry Index65.630.9
Released2026-09-292024-12-11
WeightsProprietaryOpen
Context window1.05M128K
Max output128K4K
Input $ / M tokens$2$0.075
Output $ / M tokens$10$0.30
Results tracked343

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), Phi-4 Mini: 28.1 (#317)

BenchmarkGPT-6.1 SolPhi-4 Mini
SciCode55.8%10.8%
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
LMArena Coding1487—

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
APEX-Agents60%—
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Phi-4 Mini: 22.4 (#195)

BenchmarkGPT-6.1 SolPhi-4 Mini
CritPt31.7%0%
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
Chess Puzzles61%—
EBR-Bench54.3%—
LMArena Hard Prompts1466—
Mystery Game Puzzles80%—
Epoch Capabilities Index166.09—

Math Not comparable

GPT-6.1 Sol: 93.7 (#1), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
LMArena Math1464—

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Phi-4 Mini: 25.3 (#262)

BenchmarkGPT-6.1 SolPhi-4 Mini
GPQA Diamond95.4%—
SimpleQA Verified73.9%—
Vectara Hallucination Rate—23.5%
LMArena Expert1502—

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
LMArena Vision1288—
Furniture Assembly80%—

Multilingual Not comparable

GPT-6.1 Sol: 54.3 (#46), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
LMArena Non-English1438—
LMArena Chinese1477—
LMArena Russian1455—

Instruction Following Not comparable

GPT-6.1 Sol: 77.0 (#29), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
LMArena Instruction Following1468—

Long Context Not comparable

GPT-6.1 Sol: 44.9 (#54), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
LMArena Longer Query1465—

Writing & Preference Not comparable

GPT-6.1 Sol: 63.6 (#63), Phi-4 Mini: —

BenchmarkGPT-6.1 SolPhi-4 Mini
LMArena Text1447—
LMArena Creative Writing1432—
LMArena Multi-Turn1449—

Frequently asked questions

Is GPT-6.1 Sol better than Phi-4 Mini?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.9 on the Noometry Index. Phi-4 Mini costs 30× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

Which is cheaper, GPT-6.1 Sol or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is GPT-6.1 Sol or Phi-4 Mini better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 128K.

How many benchmarks do GPT-6.1 Sol and Phi-4 Mini share?

2 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Phi-4 Mini has 3.

Related comparisons

Go deeper