Model comparison
Claude Haiku 4.5 vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 39.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Gemini 4 Argon in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 4 Argon leads 44.2 to 15.1.
- The biggest single-benchmark swing is Blueprint-Bench 2: 0% for Claude Haiku 4.5 and 54.4% for Gemini 4 Argon.
Side by side
| Claude Haiku 4.5 | Gemini 4 Argon | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 56.5 |
| Released | 2025-10-15 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
Claude Haiku 4.5: 44.0 (#78), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena WebDev | 1330 | 1678 |
| SciCode | 43.3% | 61.8% |
| LMArena Coding | 1453 | 1550 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| FrontierSWE | — | 55% |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Gemini 4 Argon leads
Claude Haiku 4.5: 33.6 (#52), Gemini 4 Argon: 49.2 (#8)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| Vending-Bench 2 | 458.89 | 13,718 |
| Terminal-Bench | 35.5% | — |
| APEX-Agents | — | 82.2% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
Reasoning Gemini 4 Argon leads
Claude Haiku 4.5: 15.1 (#320), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| CritPt | 0% | 27.1% |
| LMArena Hard Prompts | 1420 | 1548 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Gemini 4 Argon leads
Claude Haiku 4.5: 44.9 (#78), Gemini 4 Argon: 73.9 (#17)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Math | 1396 | 1536 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| ProofBench | — | 99% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Gemini 4 Argon leads
Claude Haiku 4.5: 37.7 (#153), Gemini 4 Argon: 43.9 (#89)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1442 | 1553 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Gemini 4 Argon leads
Claude Haiku 4.5: 26.8 (#118), Gemini 4 Argon: 46.5 (#14)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | 0% | 54.4% |
| LMArena Document | 1420 | — |
Multilingual Gemini 4 Argon leads
Claude Haiku 4.5: 49.9 (#129), Gemini 4 Argon: 60.3 (#1)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1377 | 1523 |
| LMArena Chinese | 1417 | 1610 |
| LMArena Russian | 1381 | 1537 |
| LMArena Spanish | 1420 | 1497 |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
Instruction Following Gemini 4 Argon leads
Claude Haiku 4.5: 71.4 (#149), Gemini 4 Argon: 80.1 (#2)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1414 | 1538 |
| IFEval | 80.1% | — |
Long Context Gemini 4 Argon leads
Claude Haiku 4.5: 43.6 (#92), Gemini 4 Argon: 47.6 (#15)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1427 | 1549 |
Writing & Preference Gemini 4 Argon leads
Claude Haiku 4.5: 57.9 (#123), Gemini 4 Argon: 71.4 (#19)
| Benchmark | Claude Haiku 4.5 | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1396 | 1534 |
| LMArena Creative Writing | 1372 | 1531 |
| LMArena Multi-Turn | 1409 | 1557 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 39.5 on the Noometry Index.
Is Claude Haiku 4.5 or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 44.0 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Gemini 4 Argon share?
18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 4 Argon has 21.