Gemini 3.5 Flash Lite vs Inkling: Benchmark Comparison
Gemini 3.5 Flash Lite has the higher score on 8 of 21 shared benchmarks; Inkling leads on 12.
The largest observed score gap is 17.95 pts on Vibe Code Bench v1.1 , where Gemini 3.5 Flash Lite leads.
Reported ±1 standard-error ranges overlap on 8 of 21 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 | Gemini 3.5 Flash Lite | Inkling | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 0.00% ±0.00 | 2.08% ±0.83 | 2.08 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 13.94% ±2.41 | 28.36% ±3.13 | 14.42 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.07% ±0.44 | 82.95% ±0.50 | 1.12 pts | Reported ±1 SE ranges do not overlap |
| EMB | 43.23% ±3.10 | 38.36% ±3.27 | 4.87 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 47.44% ±0.51 | 46.60% ±0.93 | 0.84 pts | Reported ±1 SE ranges overlap |
| MortgageTax | 68.68% ±0.91 | 63.99% ±0.94 | 4.69 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 37.45% ±3.12 | 43.52% ±2.95 | 6.06 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 72.61% ±0.88 | 75.31% ±0.84 | 2.70 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 43.49% ±1.95 | 41.19% ±2.23 | 2.30 pts | Reported ±1 SE ranges overlap |
| MedScribe | 70.89% ±2.03 | 85.41% ±1.84 | 14.52 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 83.84% ±1.85 | 87.12% ±1.78 | 3.28 pts | Reported ±1 SE ranges overlap |
| MMLU Pro | 85.84% ±0.34 | 86.30% ±0.34 | 0.46 pts | Reported ±1 SE ranges overlap |
| MMMU Pro | 83.58% ±0.89 | 78.50% ±0.99 | 5.09 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 47.30% ±3.38 | 36.55% ±3.22 | 10.75 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 6.15% ±1.71 | 11.79% ±3.40 | 5.64 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 79.01% ±1.10 | 85.52% ±1.00 | 6.50 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.00% ±0.00 | 0.00% ±0.00 | 0.00 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 75.00% ±1.94 | 77.60% ±1.87 | 2.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 37.16% ±4.63 | 19.21% ±3.66 | 17.95 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 59.11% ±6.17 | 66.79% ±5.95 | 7.68 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 51.83% ±1.30 | 58.46% ±1.28 | 6.63 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Gemini 3.5 Flash Lite average | Inkling average |
|---|---|---|
| Legal | 32.67% | 37.80% |
| Finance | 53.88% | 53.55% |
| Healthcare | 57.19% | 63.30% |
| Academic | 84.42% | 83.97% |
| Education | 47.30% | 36.55% |
| Coding | 39.46% | 38.82% |
| Cyber | 59.11% | 66.79% |
| Social Mobility | 51.83% | 58.46% |
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 | Gemini 3.5 Flash Lite cost | Inkling cost | Gemini 3.5 Flash Lite latency | Inkling latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $0.33 | $1.25 | 3m53s | 18m24s |
| Legal Research Bench | $0.12 | $0.49 | 59.20s | 14m29s |
| LegalBench | N/A | N/A | 1.67s | 23.14s |
| EMB | $1.23 | $1.67 | 8m14s | 26m22s |
| Finance Agent (v2) | $0.39 | $1.00 | 2m23s | 18m02s |
| MortgageTax | N/A | N/A | 4.88s | 69.11s |
| Tax Agent Bench | $0.08 | $0.35 | 47.46s | 13m31s |
| TaxEval v2 | N/A | N/A | 8.81s | 3m18s |
| MedCode | N/A | N/A | 6.02s | 2m47s |
| MedScribe | N/A | N/A | 18.99s | 4m05s |
| GPQA Diamond | N/A | N/A | 13.85s | 5m09s |
| MMLU Pro | N/A | N/A | 4.82s | 73.26s |
| MMMU Pro | N/A | N/A | 7.80s | 2m04s |
| SAGE | N/A | N/A | 10.75s | 3m18s |
| Code Migration | $0.53 | $3.01 | 22m02s | 29m34s |
| LiveCodeBench | N/A | N/A | 21.08s | 4m18s |
| ProgramBench | $0.34 | $4.14 | 7m15s | 45m34s |
| SWE-bench | $0.31 | $0.59 | 7m20s | 6m34s |
| Vibe Code Bench v1.1 | $0.83 | $1.61 | 8m22s | 18m25s |
| CyberBench v1.1 | $0.43 | $1.46 | 17m56s | 13m31s |
| Public Benefits Bench v1.1 | $0.10 | $0.37 | 69.26s | 13m31s |
Results available only for Gemini 3.5 Flash Lite
None.
Results available only for Inkling
- Vals Index
- ProofBench v1.1
- IOI
- SkillsBench
- Terminal-Bench 4.0
- Vibe Code Bench 1-100