Claude Haiku 5.5 vs Gemini 4 Argon
Claude Haiku 5.5 
Gemini 4 Argon Verdict
- Gemini 4 Argon (high) leads on quality: 70.0 vs 61.3.
- Gemini 4 Argon (high) is stronger in coding, composite, knowledge, long context, maths, reasoning, agents & tools, human preference.
- Claude Haiku 5.5 (high) is 20× cheaper ($0.200 vs $4.00 per 1M blended).
| Metric | Claude Haiku 5.5 (high) | Gemini 4 Argon (high) |
|---|---|---|
| BenchLeader Index | 61.3 | 70.0 |
| Coding score | 62.6 | 72.1 |
| Composite score | 72.4 | 89.2 |
| Knowledge score | 64.3 | 75.7 |
| Long context score | 63.8 | 65.0 |
| Maths score | 66.2 | 71.9 |
| Reasoning score | 72.1 | 82.0 |
| Agents & tools score | – | 67.5 |
| Human preference score | – | 73.2 |
| Blended price $/M | $0.200 | $4.00 |
| Output speed | 174 tok/s | – |
| Time to first answer | 22.6 s | – |
| Context window | 1M | 1M |
| OTIS Mock AIME | 97.2% | – |
| SciCode | – | 61.8% |
| LMArena Text | – | 1525 |
| LMArena Hard Prompts | – | 1551 |
| LMArena Coding | – | 1562 |
| LMArena WebDev | 1587 | 1678 |
| LMArena Agent | – | 9.3 |
| AA Intelligence Index v4.3.2 | 37.8 | 52.6 |
| AA-LCR | 77.3% | 79.7% |
| AA-Omniscience | 5.8 | 42.4 |
| Humanity's Last Exam (AA) | 37.3% | 57.1% |
| SciCode (AA) | 48.7% | 61.8% |
| IOI | – | 100.0% |
| LegalBench | – | 88.3% |
| Vals Index | – | 68.9 |
| CritPt | 18.6% | 27.1% |
| GDPval-AA v2.1 | 45.9% | 56.3% |
| BioMysteryBench | – | 76.3% |
| Code Migration | – | 68.2% |
| CUA-bench | – | 4.8% |
| CyberBench | – | 77.9% |
| Excel Modeling Benchmark | – | 75.2% |
| Finance Agent v2 | – | 65.4% |
| Harvey's Legal Agent Benchmark | – | 19.6% |
| Legal Research Bench | – | 54.8% |
| MedCode | – | 58.8% |
| MedScribe | – | 87.4% |
| MysteryMechanism | – | 45.5% |
| ProgramBench | – | 2.5% |
| Public Benefits Bench | – | 69.8% |
| SAGE | – | 53.6% |
| SREBench | – | 44.3% |
| Tax Agent Bench | – | 76.2% |
| Terminal-Bench 4.0 (Vals) | – | 57.6% |
| Terminal-Bench Science | – | 44.3% |
| Vibe Code Bench v1.1 | – | 91.9% |
| LMArena Maths | – | 1528 |
| LMArena Creative Writing | – | 1519 |
| LMArena Instruction Following | – | 1529 |
| LMArena Multi-turn | – | 1553 |
| LMArena Longer Queries | – | 1545 |
| FrontierSWE | – | 55.0% |
| Terminal-Bench 4.0 (AA) | 21.7% | 57.1% |
| AutomationBench | 33.7% | 77.5% |
| GDP.pdf | 17.2% | 21.8% |
| Harvey LAB | 1.1% | – |
| AA-Omniscience: accuracy | 34.8% | 49.9% |
| AA-Omniscience: non-hallucination | 55.5% | 84.9% |
| AA-Briefcase v1.1 | 1442 | 1488 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Haiku 5.5 vs Gemini 4 Argon: questions
- Is Claude Haiku 5.5 better than Gemini 4 Argon?
- Gemini 4 Argon (high) leads on quality: 70.0 vs 61.3. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Argon (high) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Haiku 5.5 better than Gemini 4 Argon for coding?
- Gemini 4 Argon scores higher in coding (72 vs 63 on the category index, where 50 is average).
- Which is cheaper, Claude Haiku 5.5 or Gemini 4 Argon?
- Claude Haiku 5.5 is cheaper: $0.200 against $4.00 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.