What is the difference between MoonshotAI: Kimi K2 0905 and GPT-5?

MoonshotAI: Kimi K2 0905 is developed by Moonshot AI while GPT-5 is developed by OpenAI. MoonshotAI: Kimi K2 0905 has a 262K token context window vs GPT-5's 400K. in 5 community votes on RIVAL, MoonshotAI: Kimi K2 0905 wins 75% of head-to-head matchups. These results are based on blind head-to-head voting across 42 challenges.

Which is better, MoonshotAI: Kimi K2 0905 or GPT-5?

Based on 5 community votes on RIVAL, MoonshotAI: Kimi K2 0905 wins 75% of head-to-head matchups against GPT-5. MoonshotAI: Kimi K2 0905 is strongest in Web Design.

How much does MoonshotAI: Kimi K2 0905 cost compared to GPT-5?

MoonshotAI: Kimi K2 0905 costs $0.6/M input tokens and GPT-5 costs $1.25/M input tokens. MoonshotAI: Kimi K2 0905 is $0.65/M cheaper per input. MoonshotAI: Kimi K2 0905 also wins more often in community votes, making it the better value.

How are MoonshotAI: Kimi K2 0905 vs GPT-5 votes collected on RIVAL?

RIVAL presents both models' outputs side-by-side in blind duels — voters see the responses but don't know which model produced each one. This eliminates brand bias. 5 votes have been collected for this pair across 42 challenges. All vote data is part of RIVAL's open dataset.

Rival

MoonshotAI: Kimi K2 0905vsGPT-5

42 challenges

Why MoonshotAI: Kimi K2 0905?

3.7x cheaper overall$0.60/M in · $2.50/M out

Why GPT-5?

1.5x more context400K

Favorites

MoonshotAI: Kimi K2 0905GPT-5

Movie

Blade Runner

19827.9

—

Album

OK Computer

Radiohead

—

Book

The Left Hand of Darkness

Ursula K. Le Guin

—

City

Kyoto

Japan

—

Game

Outer Wilds

Indie, Adventure4.4

—

12 / 42

Estimate Complexityreasoning

Tests an AI's ability to make educated estimates based on technical knowledge

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics.

Assumptions

Model size (N): GPT-3 has about 175 billion parameters (N ≈ 1.75 × 10^11).
Training tokens (T): GPT-3 was trained on roughly 300 billion tokens (T ≈ 3.0 × 10^11).
FLOPs per token per parameter: A common rule of thumb for transformer LM training is FLOPs ≈ 6 × N × T The factor ~6 comes from counting forward and backward passes for the parameter-heavy matmuls (roughly 2N for forward + 4N for backward). It ignores small terms from layernorms, softmax, embeddings, and optimizer updates (which we’ll account for with a small overhead factor later).

Core calculation

6 × N × T = 6 × (1.75 × 10^11) × (3.0 × 10^11)
First multiply N × T: 1.75 × 3.0 = 5.25; powers: 10^11 × 10^11 = 10^22 So N × T = 5.25 × 10^22
Now multiply by 6: 6 × 5.25 × 10^22 = 31.5 × 10^22 = 3.15 × 10^23 FLOPs

Overheads and uncertainty

Non-matmul ops (attention softmax, masking, residuals, layernorms), embeddings, and optimizer update steps add some overhead. A 10–20% uplift is a reasonable allowance.
Applying +10–20%: 3.15 × 10^23 × (1.1 to 1.2) ≈ (3.5 ± 0.3) × 10^23 FLOPs.

Answer

Point estimate: ~3.15 × 10^23 FLOPs
With a modest overhead allowance: roughly (3.3–3.8) × 10^23 FLOPs

This is a coarse estimate; the exact number depends on details like sequence length, activation checkpointing, implementation efficiency, and the precise token count.

Vote

2 / 42

AI Board Game Logicreasoning

Tests an AI's ability to understand game rules and strategy

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025svg

No content available for this output.

GPT-5

Openai · Aug 2025svg

Vote

3 / 42

Logic Puzzlereasoning

Tests an AI's ability to solve a simple but potentially confusing logic puzzle

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

Reason: If each of the 3 brothers has 2 sisters, there are exactly 2 girls in the family. One is Sally, so she has 1 sister.

Vote

4 / 42

Math Misconception Testreasoning

Tests an AI's understanding of number representation

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

5 / 42

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

6 / 42

Xbox Controller SVG Artimage generation

Tests an AI's ability to create detailed SVG illustrations of gaming hardware

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025svg

No content available for this output.

GPT-5

Openai · Aug 2025svg

No content available for this output.

Vote

7 / 42

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

8 / 42

Realistic AI Interviewconversation

Tests an AI's ability to simulate personalities and predict future trends

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

9 / 42

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

10 / 42

Character Voice Testconversation

Tests an AI's ability to write in distinct character voices

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

11 / 42

Minimalist Landing Pageweb design

Tests an AI's ability to generate a complete, working landing page

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025website

GPT-5

Openai · Aug 2025website

Vote

12 / 42

Mario Level UI Recreationweb design

Recreate an interactive, classic Mario level in a single HTML file.

MoonshotAI: Kimi K2 0905

Moonshotai · Sep 2025website

GPT-5

Openai · Aug 2025website

Vote

12 of 42

FAQ

Continue exploring

MoonshotAI: Kimi K2 0905 vs Llama 4 MaverickNew provider

MoonshotAI: Kimi K2 0905 vs Claude Opus 4New provider

MoonshotAI: Kimi K2 0905 vs MiniMax M1New provider

Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics.

Assumptions

Model size (N): GPT-3 has about 175 billion parameters (N ≈ 1.75 × 10^11).
Training tokens (T): GPT-3 was trained on roughly 300 billion tokens (T ≈ 3.0 × 10^11).
FLOPs per token per parameter: A common rule of thumb for transformer LM training is FLOPs ≈ 6 × N × T The factor ~6 comes from counting forward and backward passes for the parameter-heavy matmuls (roughly 2N for forward + 4N for backward). It ignores small terms from layernorms, softmax, embeddings, and optimizer updates (which we’ll account for with a small overhead factor later).

Core calculation

6 × N × T = 6 × (1.75 × 10^11) × (3.0 × 10^11)
First multiply N × T: 1.75 × 3.0 = 5.25; powers: 10^11 × 10^11 = 10^22 So N × T = 5.25 × 10^22
Now multiply by 6: 6 × 5.25 × 10^22 = 31.5 × 10^22 = 3.15 × 10^23 FLOPs

Overheads and uncertainty

Non-matmul ops (attention softmax, masking, residuals, layernorms), embeddings, and optimizer update steps add some overhead. A 10–20% uplift is a reasonable allowance.
Applying +10–20%: 3.15 × 10^23 × (1.1 to 1.2) ≈ (3.5 ± 0.3) × 10^23 FLOPs.

Answer

Point estimate: ~3.15 × 10^23 FLOPs
With a modest overhead allowance: roughly (3.3–3.8) × 10^23 FLOPs

This is a coarse estimate; the exact number depends on details like sequence length, activation checkpointing, implementation efficiency, and the precise token count.