Claude Opus 5.5 vs Gemini 4 Argon: Benchmark Comparison
Claude Opus 5.5 has the higher score on 21 of 30 shared benchmarks; Gemini 4 Argon leads on 9.
The largest observed score gap is 38.83 pts on Time Horizon Index: KSP , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 13 of 27 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.
Shared benchmark results
Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.
| Benchmark | Claude Opus 5.5 | Gemini 4 Argon | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 65.59% ±1.48 | 64.89% ±1.49 | 0.70 pts | Reported ±1 SE ranges overlap |
| Vals Index | 70.18% ±1.00 | 69.24% ±1.09 | 0.94 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 72.33% ±1.84 | 76.72% ±1.84 | 4.38 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 30.55% | 6.76 pts | Uncertainty comparison unavailable |
| Vals Science Index | 58.65% ±2.32 | 55.36% ±2.29 | 3.29 pts | Reported ±1 SE ranges overlap |
| HLAB-Vals-1.1 | 9.17% ±2.37 | 27.08% ±3.74 | 17.92 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 50.48% ±3.48 | 54.81% ±3.46 | 4.33 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 75.84% ±2.41 | 74.83% ±2.49 | 1.01 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 67.85% ±2.05 | 67.66% ±2.00 | 0.19 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 45.57% ±3.59 | 44.56% ±3.59 | 1.01 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.80% ±2.27 | 58.80% ±2.10 | 9.00 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 91.43% ±1.93 | 87.43% ±1.96 | 4.00 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 99.00% ±1.00 | 1.00 pts | Reported ±1 SE ranges overlap |
| BioMysteryBench | 79.26% ±0.98 | 76.30% ±0.37 | 2.96 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 49.55% ±3.36 | 45.49% ±3.35 | 4.05 pts | Reported ±1 SE ranges overlap |
| Robo-bench | 14.58% | 0.83% | 13.75 pts | Uncertainty comparison unavailable |
| Terminal-Bench-Science | 47.14% ±6.01 | 44.29% ±5.98 | 2.86 pts | Reported ±1 SE ranges overlap |
| SAGE | 45.83% ±3.36 | 53.65% ±3.38 | 7.81 pts | Reported ±1 SE ranges do not overlap |
| Code Migration v1.1 | 81.01% ±3.21 | 70.80% ±3.72 | 10.22 pts | Reported ±1 SE ranges do not overlap |
| IOI | 95.06% ±4.94 | 100.00% ±0.00 | 4.94 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 18.50% ±2.75 | 2.50% ±1.11 | 16.00 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 70.21% ±2.09 | 56.04% ±2.27 | 14.17 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 57.58% ±2.31 | 7.58 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 30.36% ±4.83 | 21.20% ±3.81 | 9.16 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 91.91% ±1.90 | 1.61 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 77.86% ±5.30 | 22.50 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 33.59% ±2.92 | 44.27% ±3.08 | 10.69 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 70.64% ±1.19 | 69.76% ±0.00 | 0.88 pts | Reported ±1 SE ranges overlap |
| CUA-bench | 14.00% | 4.83% | 9.17 pts | Uncertainty comparison unavailable |
| Time Horizon Index: KSP | 91.33% ±0.00 | 52.50% ±8.86 | 38.83 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 5.5 average | Gemini 4 Argon average |
|---|---|---|
| Legal | 29.82% | 40.95% |
| Finance | 63.09% | 62.35% |
| Healthcare | 70.61% | 73.11% |
| Math | 100.00% | 99.00% |
| Science | 47.63% | 41.73% |
| Education | 45.83% | 53.65% |
| Coding | 64.37% | 57.15% |
| Cyber | 44.47% | 61.07% |
| Social Mobility | 70.64% | 69.76% |
Cost and latency
Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.
| Benchmark | Claude Opus 5.5 cost | Gemini 4 Argon cost | Claude Opus 5.5 latency | Gemini 4 Argon latency |
|---|---|---|---|---|
| Vals Finance Index | $11.67 | $6.53 | 45m00s | 22m41s |
| Vals Index | $28.12 | $13.37 | 1h25m | 44m58s |
| Vals Legal Index | $20.54 | $6.82 | 1h19m | 25m41s |
| Vals RSI Index | $411.86 | $179.80 | 90h00m | 90h00m |
| Vals Science Index | $9.13 | $18.40 | 59m51s | 57m00s |
| HLAB-Vals-1.1 | $21.38 | $10.55 | 58m27s | 29m15s |
| Legal Research Bench | $25.16 | $6.45 | 1h52m | 31m21s |
| EMB v1.1 | $11.02 | $11.80 | 35m06s | 38m26s |
| Finance Agent v2.1 | $8.91 | $4.32 | 33m00s | 13m13s |
| Tax Agent Bench | $15.09 | $3.47 | 1h07m | 16m26s |
| MedCode | N/A | N/A | 4m07s | 79.53s |
| MedScribe | N/A | N/A | 7m22s | 87.44s |
| ProofBench v1.1 | $0.96 | $0.78 | 5m51s | 6m20s |
| BioMysteryBench | $3.64 | $5.71 | 12m19s | 39m57s |
| MysteryMechanism | $4.62 | $4.59 | 19m38s | 24m55s |
| Robo-bench | $11.38 | $17.33 | 2m07s | 2m32s |
| Terminal-Bench-Science | $19.12 | $44.90 | 2h28m | 1h46m |
| SAGE | N/A | N/A | 114.20s | 63.07s |
| Code Migration v1.1 | $72.40 | $44.79 | 3h29m | 2h22m |
| IOI | $5.26 | $5.31 | 17m15s | 24m19s |
| ProgramBench | $68.05 | $17.66 | 2h24m | 1h11m |
| SWE-bench Multimodal | $4.92 | $11.40 | 18m32s | 33m38s |
| Terminal-Bench 4.0 | $13.20 | $17.64 | 1h04m | 53m35s |
| Vibe Code Bench 1-100 | $44.12 | $18.66 | 2h28m | 1h43m |
| Vibe Code Bench v1.1 | $57.92 | $8.11 | 1h36m | 37m28s |
| CyberBench v1.1 | $3.48 | $5.11 | 18m11s | 19m10s |
| SRE Bench | $34.65 | $30.45 | 1h37m | 1h35m |
| Public Benefits Bench v1.1 | $5.95 | $2.79 | 1h20m | 26m07s |
| CUA-bench | $188.04 | $193.78 | 14.71s | 70.51s |
| Time Horizon Index: KSP | $1303.37 | $708.63 | N/A | N/A |
Results available only for Claude Opus 5.5
- ClaimBench
Results available only for Gemini 4 Argon
- LegalBench