Claude Haiku 5.5 vs GPT-5.6 Terra
GPT-5.6 Terra leads Claude Haiku 5.5 by 1.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 7 and GPT-5.6 Terra wins 11 of 19 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Haiku 5.5 | GPT-5.6 Terra |
|---|---|---|
| Agentic coding | 67 | 66 |
| Long-horizon autonomy | 62 | 69 |
| Knowledge-work agents | 46 | 47 |
| Computer use | 47 | 48 |
| Security & context learning | 55 | 56 |
Shared benchmarks
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Terra |
|---|---|---|
| APEX-Agentsindex | 56.1% | 58.2% |
| Vending-Bench 2index | $3,602 | $7,343 |
| CursorBenchindex | 48.4% | 41.3% |
| ARC-AGI | 89.0% | 96.5% |
| ARC-AGI-2 | 61.3% | 83.9% |
| Chess Puzzles | 55.0% | 47.0% |
| CritPt | 22.6% | 30.0% |
| DTBench | 95.0% | 93.3% |
| FrontierCode | 46.4% | 41.3% |
| FrontierMath Tier 4 | 46.3% | 70.7% |
| FrontierMath Tiers 1-3 | 75.1% | 86.0% |
| GPQA Diamond | 89.6% | 93.3% |
| LMCA | 51.1% | 54.9% |
| MirrorCode | 78.9% | 41.1% |
| OTIS Mock AIME | 98.9% | 99.7% |
| ProofBench | 89.0% | 74.0% |
| SciCode | 55.0% | 55.0% |
| SimpleBench | 59.2% | 48.9% |
| SimpleQA Verified | 23.8% | 43.2% |
Specs and price
| Claude Haiku 5.5 | GPT-5.6 Terra | |
|---|---|---|
| Agent Index | 57.5 (#18) | 58.8 (#16) |
| Agent $/M | $0.050 | $1.02 |
| Input / output $/M | $0.10 / $0.50 | $2.00 / $12.00 |
| Context | 1M | 1.1M |
| Released | Oct 7, 2026 | Jul 9, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 4 |
Don’t pick one. Route.
Shogo can run Claude Haiku 5.5 and GPT-5.6 Terra side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo