Model comparison
GPT-4.1 mini vs GPT-5.6 Terra
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 33.6 on the Noometry Index. GPT-4.1 mini costs 6.4× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and GPT-5.6 Terra in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 96.5% for GPT-5.6 Terra.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-4.1 mini | GPT-5.6 Terra | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 59.2 |
| Released | 2025-04-14 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $1.60 | $12 |
| Results tracked | 47 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-4.1 mini: 30.6 (#293), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| SciCode | 40.4% | 55% |
| WeirdML | 37.6% | 78.3% |
| LMArena Coding | 1367 | 1484 |
| DeepSWE | — | 69.6% |
| FrontierCode | — | 41.3% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| CursorBench | — | 41.3% |
| LMArena WebDev | — | 1522 |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,951 |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-4.1 mini: 33.3 (#55), GPT-5.6 Terra: 40.1 (#25)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | — | 58.2% |
| Berkeley Function Calling Leaderboard | 50.5% | — |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
GPT-4.1 mini: 10.8 (#340), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| ARC-AGI-2 | 0% | 83.9% |
| Kagi LLM Benchmark | 48.6% | 51.3% |
| ARC-AGI-1 | 3.5% | 96.5% |
| CritPt | 0% | 30% |
| Chess Puzzles | 7% | 54% |
| LMArena Hard Prompts | 1349 | 1468 |
| Mystery Game Puzzles | 7% | 35% |
| DTBench | 68.8% | 93.3% |
| LMCA | 21.1% | 55% |
| Epoch Capabilities Index | 135.01 | 159.62 |
| SimpleBench | — | 48.9% |
| NYT Connections (extended) | — | 78.4% |
| Surface Evolver Bench | — | 83.8% |
Math GPT-5.6 Terra leads
GPT-4.1 mini: 24.1 (#270), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 86% |
| OTIS Mock AIME 2024-2025 | 44.7% | 99.7% |
| LMArena Math | 1343 | 1466 |
| FrontierMath Tier 4 | — | 70.7% |
| ProofBench | — | 74% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge GPT-5.6 Terra leads
GPT-4.1 mini: 34.7 (#194), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| GPQA Diamond | 65.8% | 93.3% |
| SimpleQA Verified | 12.7% | 43.2% |
| LMArena Expert | 1338 | 1492 |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal GPT-5.6 Terra leads
GPT-4.1 mini: 35.8 (#82), GPT-5.6 Terra: 47.3 (#11)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | 1181 | 1271 |
| Blueprint-Bench 2 | — | 30.8% |
| Furniture Assembly | — | 54.2% |
| LMArena Document | — | 1472 |
Multilingual GPT-5.6 Terra leads
GPT-4.1 mini: 45.7 (#166), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1318 | 1439 |
| LMArena Chinese | 1329 | 1513 |
| LMArena French | 1358 | 1471 |
| LMArena German | 1351 | 1460 |
| LMArena Japanese | 1290 | 1457 |
| LMArena Korean | 1298 | 1425 |
| LMArena Russian | 1324 | 1450 |
| LMArena Spanish | 1319 | 1448 |
Instruction Following GPT-5.6 Terra leads
GPT-4.1 mini: 73.7 (#118), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1333 | 1454 |
| IFEval | 90.4% | — |
Long Context GPT-5.6 Terra leads
GPT-4.1 mini: 31.8 (#275), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1344 | 1451 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5.6 Terra leads
GPT-4.1 mini: 48.6 (#199), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | GPT-4.1 mini | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1340 | 1447 |
| LMArena Creative Writing | 1300 | 1410 |
| EQ-Bench Creative Writing | 1147 | 1855 |
| LMArena Multi-Turn | 1354 | 1449 |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1234 |
Frequently asked questions
Is GPT-4.1 mini better than GPT-5.6 Terra?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 33.6 on the Noometry Index. GPT-4.1 mini costs 6.4× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or GPT-5.6 Terra?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-4.1 mini or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-4.1 mini and GPT-5.6 Terra share?
34 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5.6 Terra has 52.