Model comparison
Claude Haiku 4.5 vs Trinity Large Thinking
Claude Haiku 4.5 and Trinity Large Thinking score almost the same on the Noometry Index (39.5 vs 38.6), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Arcee AISummary
- They share 22 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 6 categories and Trinity Large Thinking in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Haiku 4.5 leads 44.0 to 34.1.
- The biggest single-benchmark swing is SciCode: 43.3% for Claude Haiku 4.5 and 36.1% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Trinity Large Thinking accepts more context: 262K tokens versus 200K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Trinity Large Thinking | |
|---|---|---|
| Provider | Anthropic | Arcee AI |
| Noometry Index | 39.5 | 38.6 |
| Released | 2025-10-15 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 80K |
| Input $ / M tokens | $1 | $0.25 |
| Output $ / M tokens | $5 | $0.80 |
| Results tracked | 53 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1330 | 1238 |
| SciCode | 43.3% | 36.1% |
| LMArena Coding | 1453 | 1381 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Trinity Large Thinking: —
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Trinity Large Thinking leads
Claude Haiku 4.5: 15.1 (#320), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 14.3% | 16.5% |
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1420 | 1350 |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1396 | 1366 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Trinity Large Thinking leads
Claude Haiku 4.5: 37.7 (#153), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 9.8% | 6.9% |
| LMArena Expert | 1442 | 1360 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Trinity Large Thinking: —
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1377 | 1325 |
| LMArena Chinese | 1417 | 1373 |
| LMArena French | 1408 | 1374 |
| LMArena German | 1375 | 1356 |
| LMArena Japanese | 1339 | 1311 |
| LMArena Korean | 1347 | 1306 |
| LMArena Russian | 1381 | 1337 |
| LMArena Spanish | 1420 | 1357 |
Instruction Following Too close to call
Claude Haiku 4.5: 71.4 (#149), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1414 | 1334 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1427 | 1355 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Claude Haiku 4.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1396 | 1340 |
| LMArena Creative Writing | 1372 | 1320 |
| LMArena Multi-Turn | 1409 | 1342 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Trinity Large Thinking?
Claude Haiku 4.5 and Trinity Large Thinking score almost the same on the Noometry Index (39.5 vs 38.6), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Haiku 4.5 or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Trinity Large Thinking better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Trinity Large Thinking share?
22 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Trinity Large Thinking has 24.