Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
DeepSeek V4 Pro (Max) vs Gemini 3.5 Flash High: benchmark scores, pricing & comparison.
Side-by-side DeepSeek V4 Pro (Max) vs Gemini 3.5 Flash High comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #13 vs #15AskClash overall scores 59.9 vs 59.5.
Pricing $1.74/$3.48 vs $1.50/$9.00Input and output token prices per 1M tokens when published.
Open Weight vs ProprietaryDeepSeek vs Google.
DeepSeek V4 Pro (Max) vs Gemini 3.5 Flash High benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | DeepSeek V4 Pro (Max) | Gemini 3.5 Flash High |
|---|---|---|
| Overall Score | 59.9 | 59.5 |
| Leaderboard Rank | #13 | #15 |
| RWT | 8.0 | 7.0 |
| HLE | 37.7 | 40.2 |
| GPQA | 90.1 | 92.2 |
| MATH-500 | 64.5 | — |
| IFEval | — | 76.3 |
| SWE-bench | 80.6 | — |
| SWE-Pro | 55.4 | 55.1 |
| Terminal-Bench | 67.9 | 76.2 |
| LiveCodeBench | 93.5 | — |
| OSWorld | — | 78.4 |
| MCP Atlas | 73.6 | 83.6 |
| Finance Agent | — | 57.9 |
| CharXiv | — | 84.2 |
| MMMU-Pro | — | 83.6 |
| ARC-AGI 2 | — | 72.1 |
| Tau2 | 96.2 | 95.3 |
| MRCR | 83.5 | 77.3 |
| Input Price (per 1M tokens) | $1.74 | $1.50 |
| Output Price (per 1M tokens) | $3.48 | $9.00 |
| Context Window | 1M | 1M |
| Benchmark Cells | 10 | 14 |
More DeepSeek V4 Pro (Max) and Gemini 3.5 Flash High comparisons
Explore how DeepSeek V4 Pro (Max) and Gemini 3.5 Flash High stack up against other top-ranked LLMs.
Claude Mythos/Fable 5 vs DeepSeek V4 Pro (Max)Claude Mythos/Fable 5 vs Gemini 3.5 Flash HighClaude Opus 4.8 (Adaptive) vs DeepSeek V4 Pro (Max)Claude Opus 4.8 (Adaptive) vs Gemini 3.5 Flash HighGPT-5.5 xHigh vs DeepSeek V4 Pro (Max)GPT-5.5 xHigh vs Gemini 3.5 Flash HighGLM-5.2 vs DeepSeek V4 Pro (Max)GLM-5.2 vs Gemini 3.5 Flash HighClaude Opus 4.7 (Adaptive) vs DeepSeek V4 Pro (Max)Claude Opus 4.7 (Adaptive) vs Gemini 3.5 Flash High
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.