Model comparison
GPT-5.4 nano vs Sonar
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in math, where GPT-5.4 nano leads 40.7 to 31.3.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $1 / $1 for Sonar.
- GPT-5.4 nano accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5.4 nano | Sonar | |
|---|---|---|
| Provider | OpenAI | Perplexity |
| Noometry Index | 41.9 | 37.8 |
| Released | 2026-03-17 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.20 | $1 |
| Output $ / M tokens | $1.25 | $1 |
| Results tracked | 40 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.4 nano: 43.1 (#82), Sonar: 35.1 (#217)
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1404 | — |
| ALE-Bench | 1,005 | — |
Reasoning GPT-5.4 nano leads
GPT-5.4 nano: 23.8 (#159), Sonar: 20.3 (#221)
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1380 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.78 | — |
| ForecastBench | 57.3 | — |
| LiveBench | — | 46.9% |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.7 (#76), Sonar: 31.3 (#197)
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1406 | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Not comparable
GPT-5.4 nano: 41.8 (#94), Sonar: —
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
| LMArena Expert | 1397 | — |
Multimodal Not comparable
GPT-5.4 nano: 36.0 (#73), Sonar: —
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual Not comparable
GPT-5.4 nano: 48.8 (#136), Sonar: —
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1396 | — |
| LMArena German | 1368 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1321 | — |
| LMArena Russian | 1363 | — |
| LMArena Spanish | 1368 | — |
Instruction Following Too close to call
GPT-5.4 nano: 72.1 (#139), Sonar: 71.5 (#146)
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1362 | — |
Long Context Not comparable
GPT-5.4 nano: 41.6 (#131), Sonar: —
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| LMArena Longer Query | 1365 | — |
Writing & Preference GPT-5.4 nano leads
GPT-5.4 nano: 55.9 (#137), Sonar: 52.6 (#166)
| Benchmark | GPT-5.4 nano | Sonar |
|---|---|---|
| LMArena Text | 1372 | — |
| LMArena Creative Writing | 1313 | — |
| LMArena Multi-Turn | 1382 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is GPT-5.4 nano better than Sonar?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 37.8 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or Sonar?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Sonar lists at $1 and $1.
Is GPT-5.4 nano or Sonar better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 128K.
How many benchmarks do GPT-5.4 nano and Sonar share?
0 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Sonar has 7.