deepseek-flash vs gemini-3.8-flash
Parameters, independent leaderboard coverage, real-task reports and open-weight availability are shown side by side; missing coverage is not a zero.
Parameters
| Comparison item | deepseek-flash | gemini-3.8-flash |
|---|---|---|
| Model Type | LLM | LLM |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Maximum output | 384,000 tokens | 65,536 tokens |
| Input/output modalities | text, image → text | text, image, video, audio, pdf → text |
| Endpoint | openai · openai-response · anthropic | openai · gemini |
| Open weights | Available | Unavailable |
| License | MIT | Proprietary hosted model |
Leaderboard coverage
Every independent board covering either model is retained; an em dash means that board has not published a figure for that model.
A row marked as retrieved on different dates holds two readings taken on different days; a board re-fits or changes version as a whole between readings, so those two figures are not directly comparable.
| Evaluation | deepseek-flash | gemini-3.8-flash |
|---|---|---|
| LMArena Text Arena — Arena score (Elo) | — | 1493 ±9 |
| LiveBench — Overall | 81.1 | 75.8 |
| Artificial Analysis Intelligence Index — Intelligence Index | 39 | 41 |
| SuperCLUE 智能指数 — 总分 (overall) | 71.81 | — |
| Epoch Capabilities Index (ECI) — General ECI | 155 (149 - 158) | 157 (155 - 161) |
| Vals Index — Accuracy (GDP-weighted finance, coding and legal) | 57.86 ±1.16 | 62.25 ±1.01 |
| LMArena Text Arena · Chinese — Arena score (Elo) | — | 1543 ±32 |
| LMArena Text Arena · Coding — Arena score (Elo) | — | 1535 ±16 |
| LiveBench · Coding — Coding | 80.0 | 72.5 |
| LiveBench · Agentic Coding — Agentic Coding | 77.3 | 54.2 |
| Artificial Analysis · Output Speed — Median output tokens/s | 220 | 297 |
| Artificial Analysis · GDPval-AA v2.1 — Agentic Real-World Work Tasks, (Elo-500)/2000 (%) | 55 | 46 |
| Artificial Analysis · Terminal-Bench v4.0 — Agentic Coding & Terminal Use (%) | 27 | 20 |
| Artificial Analysis · MLCR-AA — Medical Long Context Reasoning (%) Retrieved on different dates | 22.8 (retrieved 2026-09-22) | 21.7 (retrieved 2026-09-07) |
Real-task reports
deepseek-flash
- RemakeBench Launch 005: four Flash models on 14 fixtures — Fourteen fixtures spanning game building, 3D scenes, CAD, drawing and robot control, run on Qwen 3.8 Flash, DeepSeek V4.1 Flash, GLM 5.3 Flash and Gemini 3.8 Flash. Finding: No model won overall. DeepSeek V4.1 Flash delivered the best submitted Turbofan CAD result (three valid native solids, with a wrong-sign coupling and LP/HP interference) and did not pass the single-turn Rubik's Cube task. Limitation: Pass/fail labels are video judgments without a machine-readable validator, and single attempts do not establish reliability; the lab publishes no aggregate score or overall winner. Several DeepSeek clips reuse earlier records that keep V4 labels and the Vision exp setting; the two results quoted here are campaign runs added for this comparison.
- MiMo-V2.6-Flash, DeepSeek V4.1 Flash and Grok 4.7 on one game prompt — Build a playable browser game from a single prompt with Command Code's /design command. Finding: DeepSeek V4.1 Flash scored 9/10 for $0.0089 with a playable one-shot game. MiMo-V2.6-Flash also scored 9/10 at $0.005; Grok 4.7 scored 8/10 at $0.20 and needed iterations. Limitation: One prompt rated by the author, whose profile lists work for Command Code, the tool that ran the test; there is no rubric and no repeated run.
- DeepSeek V4.1 Flash and GLM 5.3 Flash recreating two game menus — Recreate the Psychonauts 2 and Metroid Prime main menus as closely as possible to the originals. Finding: DeepSeek V4.1 Flash used 412k and 466k tokens, three to four times GLM 5.3 Flash's 134k and 111k, and the author judged GLM's menus clearly better on both games. Limitation: Which menu is closer to the original is the author's own judgement on two prompts, without a scoring rubric.
- Switching a coding project from GPT-6 Astra to DeepSeek V4.1 Flash — Review an existing project, list its issues and fix them. Finding: DeepSeek V4.1 Flash found several issues, asked which to tackle first and began fixing them; Kimi's review still found problems, which were passed back to DeepSeek to correct. Limitation: One uncontrolled self-report. The author ran DeepSeek through WorkBuddy's free access, so the remark about spending nothing extra does not reflect API pricing.
- Step 5 Preview and DeepSeek V4.1 Flash on a 3D arcade game — Build Katamari Tiny, a 3D arcade game, from a single prompt. Finding: DeepSeek V4.1 Flash used 26,898 tokens against Step 5 Preview's 39,830 and, in the author's view, was faster and produced the better game. Limitation: One prompt judged by an author who names DeepSeek V4.1 Flash as their default model; the post gives no timings or quality rubric.
- DeepSeek V4.1 Flash and GLM-5.3-Flash on a Blender geometry task, run locally — Write a Blender script that builds a dodecahedron trapped inside a dodecahedron. Finding: Both models produced a correct mesh with zero intersections. DeepSeek V4.1 Flash took 20 min 15 s and 62,928 tokens at 51.8 tok/s, about a fifth of GLM-5.3-Flash's time and half its tokens, and its computed clearance matched the measured mesh (0.238); the author found GLM's picture nicer. Limitation: One local run per model on different hardware and precision: GLM ran as a third-party EXL3 quantisation on two DGX Sparks and DeepSeek as FP8 on four, so speed and token counts describe those builds, not the official weights or a hosted API.
- Three Flash models build the same koi pond locally — A koi pond build, run as a local head-to-head. Finding: All three finished cleanly with zero fixes. DeepSeek V4.1 Flash was fastest at 21 minutes and 53.3K tokens, a third of GLM-5.3-Flash's time, and the author ranked it first. Limitation: One local run per model; the post states neither the prompt nor the quantisation or runtime used.
- Step 5 Preview and DeepSeek V4.1 Flash on one Three.js scene — A Three.js scene of giant red mesas in a desert, with long shadows and a huge empty sky. Finding: DeepSeek V4.1 Flash's scene was more restrained but had clearly better ground and mesa textures and a smoother camera; Step 5 Preview added more atmosphere, a tracked sun, particle and dust effects and on-screen text. Limitation: One prompt judged by eye by the author; the post does not say how either model was accessed.
gemini-3.8-flash
- RemakeBench Launch 005: four Flash models on 14 fixtures — Fourteen fixtures spanning game building, 3D scenes, CAD, drawing and robot control, run on Qwen 3.8 Flash, DeepSeek V4.1 Flash, GLM 5.3 Flash and Gemini 3.8 Flash. Finding: No model won overall. Gemini 3.8 Flash made the fastest single-turn Rubik's Cube pass (15 min 35 s, $2.09) and was the editorial winner of the robot Eiffel Tower drawing (8 min 25 s, $1.36), but did not complete the three-move extension ($5.65) and did not deliver the required Turbofan CAD assembly. Limitation: Pass/fail labels are video judgments without a machine-readable validator, and single attempts do not establish reliability; the lab publishes no aggregate score or overall winner. Gemini's displayed costs are several times the other models' on most fixtures (for example $2.09 against $0.0957–$0.3414 on the single-turn cube), and its CAD presentation clip is operator work after the run.
- Cortex AI: GPT-6 Astra, Gemini 3.8 Flash and Fable 5.1 on two real robot tasks — Load a sandwich into a microwave and close the door; attach a 5 mm tip to a pipette. Finding: Gemini 3.8 Flash scored 13.3% on the microwave task and 30% on the pipette task, second to GPT-6 Astra (80% and 70%) and ahead of Fable 5.1 (6.7% and 20%). Limitation: The post does not say how many attempts each model had; scores are partial-credit judgements by the lab's evaluator, and the authors attribute the gap mainly to weaker depth perception in the lower-scoring models.