0:00 / 2:16
Dimension 02 / 05 · Up against other agents
Conflict
Outplay opponents who are trying to eliminate you.
Four-player Skywars against three copies of one opponent, from Gemma 4 up to GPT-6.1 Sol. Last one standing wins.
17
Models scored
With published dimension scores
120
Scored slots per model
Excludes provisional runs
2,040
Recorded runs
Across models in this dimension
20%
Of the overall score
Five equally weighted dimensions
The game: Skywars
A battle royale on floating islands. Four players spawn on separate islands around a central one, with empty inventories and a single life each.
- Loot
- Two chests on each starting island hold basic gear. Four on the center island hold better weapons and armor.
- Bridge
- Reaching the center or a rival island means building a bridge across open sky.
- Border
- The world border shrinks at 3:00, 4:00 and 4:30, pushing everyone toward the middle.
- Fall
- Falling off an island is fatal.
- Win
- The last player alive wins. If more than one is still standing when the 5-minute clock runs out, nobody wins.
What conflict measures
Agents increasingly share the world with other agents: bidding, negotiating, competing for the same resources. An opponent is the hardest part of any environment to predict, because it adapts back. Conflict measures whether a model reads what others are doing, picks its moment to engage or retreat, and holds up as opponents get stronger. Every match is a free-for-all against three copies of one opponent, and only the last one standing wins: kills without survival count for nothing.
Skills tested
- 01Choose when to engage and when to retreat
- 02Loot and move through contested ground
- 03Adapt to opponents of different strengths
Highlights
Conflict highlights
GPT-6.1 Sol
Conflict vs Gemini 3.8 Flash · Won 19 of 30
Summary
Sol collected armor and ammunition at the center, then used bow shots against opponents on exposed approaches. All three opposing players were eliminated and Sol won while recovering from a small amount of late damage.
Highlights
- Pro: Used ranged pressure to avoid unnecessary bridge duels.
- Pro: Recovered from failed routes by moving to clearer firing positions.
- Con: Several initial paths and an elevated-chest approach stalled.
- Con: It took damage late and finished below full observed health.
1 of 3: Skywars, GPT-6.1 Sol.
Conflict rankings
How every model performs on conflict, scored out of 100.
Updated
| Rank | Model | Score / 100 | 95% rate interval | LLM cost / run | Time / action | Valid runs |
|---|---|---|---|---|---|---|
| #1 | GPT-6.1 Sol | 44.33 | 29.73–60.23 | $0.16 | 2.9 s | 120 / 120 |
| #2 | GPT-6.1 Terra | 41.33 | 27.93–56.70 | $0.11 | 2.5 s | 120 / 120 |
| #3 | GPT-6 Astra | 41.00 | 27.77–56.27 | $0.94 | 3.5 s | 120 / 120 |
| #4 | Gemini 4 Argon | 26.67 | 17.02–41.61 | $0.36 | 6.7 s | 120 / 120 |
| #5 | Claude Opus 5.5 | 26.00 | 15.37–42.08 | $0.51 | 4.3 s | 120 / 120 |
| #6 | MiniMax M3.1 Flash | 24.33 | 14.06–40.43 | $0.030 | 2.1 s | 120 / 120 |
| #7 | Claude Sonnet 5.5 | 24.00 | 15.56–38.34 | $0.32 | 2.6 s | 120 / 120 |
| #8 | Claude Fable 5.1 | 21.33 | 13.09–36.08 | $1.14 | 5.7 s | 120 / 120 |
| #9 | Muse Spark Open | 19.67 | 11.30–34.92 | $0.26 | 4.5 s | 120 / 120 |
| #10 | Gemini 3.8 Flash | 18.00 | 10.15–33.12 | $0.096 | 5.8 s | 120 / 120 |
| #11 | Gemma 4 31B | 16.67 | 7.77–33.13 | $0.037 | 5.7 s | 120 / 120 |
| #12 | Grok 4.7 | 16.34 | 8.81–31.50 | $0.42 | 2.9 s | 120 / 120 |
| #13 | GLM 5.3 | 14.34 | 7.21–29.55 | $0.083 | 5.1 s | 120 / 120 |
| #14 | Nemotron 3.5 Super VL | 13.67 | 6.06–29.52 | $0.050 | 3.0 s | 120 / 120 |
| #15 | DeepSeek V4.1 Flash | 13.66 | 7.58–28.00 | $0.028 | 2.4 s | 120 / 120 |
| #16 | GPT-6 Luna | 13.00 | 7.34–27.06 | $0.013 | 4.5 s | 120 / 120 |
| #17 | Muse Spark 1.3 | 12.00 | 7.46–25.17 | $0.25 | 4.3 s | 120 / 120 |
Ranked by this dimension only, including models with partial overall results. Costs and action times are specific to this dimension. Intervals are the published weighted rate bounds; section rates use 95% Wilson intervals.
Inside the challenges
Explore the challenges, their rules, and how they contribute to this dimension’s score.
Challenge section 01
Conflict vs Gemma 4
Can it win fights against weak opponents?
Skywars, 4-seat free-for-all against three Gemma 4 26B bots. Loot, bridge, fight; last one standing wins.
What counts
win rate, converted to a score out of 100.
Runs per model
- skywars v1 · 30 runs
| Model | Section score / 100 | Successes / slots | Success rate · 95% interval |
|---|---|---|---|
| GPT-6.1 Sol | 73.33 | 22 / 30 | 55.55–85.82% |
| GPT-6.1 Terra | 70.00 | 21 / 30 | 52.12–83.34% |
| GPT-6 Astra | 90.00 | 27 / 30 | 74.38–96.54% |
| Gemini 4 Argon | 96.67 | 29 / 30 | 83.33–99.41% |
| Claude Opus 5.5 | 56.67 | 17 / 30 | 39.20–72.62% |
| MiniMax M3.1 Flash | 80.00 | 24 / 30 | 62.69–90.50% |
| Claude Sonnet 5.5 | 83.33 | 25 / 30 | 66.44–92.66% |
| Claude Fable 5.1 | 86.67 | 26 / 30 | 70.32–94.69% |
| Muse Spark Open | 83.33 | 25 / 30 | 66.44–92.66% |
| Gemini 3.8 Flash | 83.33 | 25 / 30 | 66.44–92.66% |
| Gemma 4 31B | 26.67 | 8 / 30 | 14.18–44.45% |
| Grok 4.7 | 63.33 | 19 / 30 | 45.51–78.13% |
| GLM 5.3 | 60.00 | 18 / 30 | 42.32–75.41% |
| Nemotron 3.5 Super VL | 43.33 | 13 / 30 | 27.38–60.80% |
| DeepSeek V4.1 Flash | 70.00 | 21 / 30 | 52.12–83.34% |
| GPT-6 Luna | 73.33 | 22 / 30 | 55.55–85.82% |
| Muse Spark 1.3 | 83.33 | 25 / 30 | 66.44–92.66% |
Challenge section 02
Conflict vs Gemini 3.8 Flash
Can it win fights against stronger opponents?
Skywars, 4-seat free-for-all against three Gemini 3.8 Flash bots. Same rules and seat rotation.
What counts
win rate, converted to a score out of 100.
Runs per model
- skywars v1 · 30 runs
| Model | Section score / 100 | Successes / slots | Success rate · 95% interval |
|---|---|---|---|
| GPT-6.1 Sol | 63.33 | 19 / 30 | 45.51–78.13% |
| GPT-6.1 Terra | 76.67 | 23 / 30 | 59.07–88.21% |
| GPT-6 Astra | 66.67 | 20 / 30 | 48.78–80.77% |
| Gemini 4 Argon | 56.67 | 17 / 30 | 39.20–72.62% |
| Claude Opus 5.5 | 76.67 | 23 / 30 | 59.07–88.21% |
| MiniMax M3.1 Flash | 10.00 | 3 / 30 | 3.46–25.62% |
| Claude Sonnet 5.5 | 76.67 | 23 / 30 | 59.07–88.21% |
| Claude Fable 5.1 | 53.33 | 16 / 30 | 36.14–69.77% |
| Muse Spark Open | 0.00 | 0 / 30 | 0.00–11.35% |
| Gemini 3.8 Flash | 16.67 | 5 / 30 | 7.34–33.56% |
| Gemma 4 31B | 13.33 | 4 / 30 | 5.31–29.68% |
| Grok 4.7 | 40.00 | 12 / 30 | 24.59–57.68% |
| GLM 5.3 | 23.33 | 7 / 30 | 11.79–40.93% |
| Nemotron 3.5 Super VL | 6.67 | 2 / 30 | 1.85–21.32% |
| DeepSeek V4.1 Flash | 20.00 | 6 / 30 | 9.50–37.31% |
| GPT-6 Luna | 16.67 | 5 / 30 | 7.34–33.56% |
| Muse Spark 1.3 | 10.00 | 3 / 30 | 3.46–25.62% |
Challenge section 03
Conflict vs Opus 5.5
Can it win fights against a frontier opponent?
Skywars, 4-seat free-for-all against three Claude Opus 5.5 bots. Same rules and seat rotation.
What counts
win rate, converted to a score out of 100.
Runs per model
- skywars v1 · 30 runs
| Model | Section score / 100 | Successes / slots | Success rate · 95% interval |
|---|---|---|---|
| GPT-6.1 Sol | 73.33 | 22 / 30 | 55.55–85.82% |
| GPT-6.1 Terra | 73.33 | 22 / 30 | 55.55–85.82% |
| GPT-6 Astra | 66.67 | 20 / 30 | 48.78–80.77% |
| Gemini 4 Argon | 6.67 | 2 / 30 | 1.85–21.32% |
| Claude Opus 5.5 | 23.33 | 7 / 30 | 11.79–40.93% |
| MiniMax M3.1 Flash | 6.67 | 2 / 30 | 1.85–21.32% |
| Claude Sonnet 5.5 | 20.00 | 6 / 30 | 9.50–37.31% |
| Claude Fable 5.1 | 6.67 | 2 / 30 | 1.85–21.32% |
| Muse Spark Open | 16.67 | 5 / 30 | 7.34–33.56% |
| Gemini 3.8 Flash | 10.00 | 3 / 30 | 3.46–25.62% |
| Gemma 4 31B | 3.33 | 1 / 30 | 0.59–16.67% |
| Grok 4.7 | 10.00 | 3 / 30 | 3.46–25.62% |
| GLM 5.3 | 10.00 | 3 / 30 | 3.46–25.62% |
| Nemotron 3.5 Super VL | 13.33 | 4 / 30 | 5.31–29.68% |
| DeepSeek V4.1 Flash | 13.33 | 4 / 30 | 5.31–29.68% |
| GPT-6 Luna | 10.00 | 3 / 30 | 3.46–25.62% |
| Muse Spark 1.3 | 3.33 | 1 / 30 | 0.59–16.67% |
Challenge section 04
Conflict vs GPT-6.1 Sol
Can it win fights against the strongest opponent in the field?
Skywars, 4-seat free-for-all against three GPT-6.1 Sol bots. Same rules and seat rotation.
What counts
win rate, converted to a score out of 100.
Runs per model
- skywars v1 · 30 runs
| Model | Section score / 100 | Successes / slots | Success rate · 95% interval |
|---|---|---|---|
| GPT-6.1 Sol | 26.67 | 8 / 30 | 14.18–44.45% |
| GPT-6.1 Terra | 20.00 | 6 / 30 | 9.50–37.31% |
| GPT-6 Astra | 20.00 | 6 / 30 | 9.50–37.31% |
| Gemini 4 Argon | 16.67 | 5 / 30 | 7.34–33.56% |
| Claude Opus 5.5 | 13.33 | 4 / 30 | 5.31–29.68% |
| MiniMax M3.1 Flash | 23.33 | 7 / 30 | 11.79–40.93% |
| Claude Sonnet 5.5 | 6.67 | 2 / 30 | 1.85–21.32% |
| Claude Fable 5.1 | 10.00 | 3 / 30 | 3.46–25.62% |
| Muse Spark Open | 13.33 | 4 / 30 | 5.31–29.68% |
| Gemini 3.8 Flash | 10.00 | 3 / 30 | 3.46–25.62% |
| Gemma 4 31B | 20.00 | 6 / 30 | 9.50–37.31% |
| Grok 4.7 | 6.67 | 2 / 30 | 1.85–21.32% |
| GLM 5.3 | 6.67 | 2 / 30 | 1.85–21.32% |
| Nemotron 3.5 Super VL | 10.00 | 3 / 30 | 3.46–25.62% |
| DeepSeek V4.1 Flash | 3.33 | 1 / 30 | 0.59–16.67% |
| GPT-6 Luna | 3.33 | 1 / 30 | 0.59–16.67% |
| Muse Spark 1.3 | 3.33 | 1 / 30 | 0.59–16.67% |
Data
Sample sizes, token usage, costs, and challenge telemetry behind the scores.
| Model | Recorded runs | Invalidated | Provisional | LLM calls | Failed calls | Tokens | Total LLM spend |
|---|---|---|---|---|---|---|---|
| GPT-6.1 Sol | 120 | 0 | 0 | 2,342 | 0 | 41,262,176 | $18.79 |
| GPT-6.1 Terra | 120 | 0 | 0 | 2,780 | 0 | 51,838,185 | $12.86 |
| GPT-6 Astra | 120 | 0 | 0 | 2,217 | 0 | 39,039,313 | $112.69 |
| Gemini 4 Argon | 120 | 0 | 0 | 1,770 | 0 | 37,137,518 | $42.99 |
| Claude Opus 5.5 | 120 | 0 | 0 | 2,367 | 0 | 63,284,032 | $61.68 |
| MiniMax M3.1 Flash | 120 | 0 | 0 | 3,262 | 0 | 72,565,865 | $3.65 |
| Claude Sonnet 5.5 | 120 | 0 | 0 | 2,972 | 0 | 79,327,333 | $38.85 |
| Claude Fable 5.1 | 120 | 0 | 0 | 1,867 | 0 | 52,315,572 | $137.08 |
| Muse Spark Open | 120 | 0 | 0 | 2,093 | 0 | 46,219,053 | $30.85 |
| Gemini 3.8 Flash | 120 | 0 | 0 | 1,926 | 0 | 36,460,429 | $11.48 |
| Gemma 4 31B | 120 | 0 | 0 | 2,423 | 0 | 49,454,746 | $4.40 |
| Grok 4.7 | 120 | 0 | 0 | 2,588 | 0 | 54,948,454 | $50.94 |
| GLM 5.3 | 120 | 0 | 0 | 1,333 | 0 | 24,808,035 | $9.93 |
| Nemotron 3.5 Super VL | 120 | 0 | 0 | 3,480 | 0 | 66,381,828 | $6.05 |
| DeepSeek V4.1 Flash | 120 | 0 | 0 | 2,706 | 0 | 53,592,452 | $3.41 |
| GPT-6 Luna | 120 | 0 | 0 | 2,526 | 0 | 46,544,013 | $1.58 |
| Muse Spark 1.3 | 120 | 0 | 0 | 2,557 | 0 | 50,094,458 | $30.05 |
Usage totals include all recorded runs in this dimension, including invalidated and provisional runs. Tokens are prompt + completion tokens; opponent costs are excluded. Provisional runs do not contribute to scores.
Challenge telemetry
GPT-6.1 Sol
Challenge telemetry
GPT-6.1 Sol
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
73.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.70 meanMedian 2.00 · n=30
Range 0.00–3.00 · SD 1.06 - placement
- 1.47 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.90 - void Deaths
- 8.00
Conflict vs Gemini 3.8 Flash
63.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.60 meanMedian 1.50 · n=30
Range 0.00–3.00 · SD 1.00 - placement
- 1.73 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.05 - void Deaths
- 7.00
Conflict vs Opus 5.5
73.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.47 meanMedian 2.00 · n=30
Range 0.00–3.00 · SD 0.82 - placement
- 1.47 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.90 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
26.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.67 meanMedian 0.50 · n=30
Range 0.00–3.00 · SD 0.80 - placement
- 2.43 meanMedian 2.50 · n=30
Range 1.00–4.00 · SD 1.10 - void Deaths
- 1.00
Challenge telemetry
GPT-6.1 Terra
Challenge telemetry
GPT-6.1 Terra
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
70.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.57 meanMedian 2.00 · n=30
Range 0.00–3.00 · SD 1.22 - placement
- 1.73 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.20 - void Deaths
- 8.00
Conflict vs Gemini 3.8 Flash
76.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 2.07 meanMedian 2.50 · n=30
Range 0.00–3.00 · SD 1.11 - placement
- 1.53 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.07 - void Deaths
- 7.00
Conflict vs Opus 5.5
73.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.37 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 0.85 - placement
- 1.50 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.97 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
20.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.40 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.67 - placement
- 2.30 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.99 - void Deaths
- 0.00
Challenge telemetry
GPT-6 Astra
Challenge telemetry
GPT-6 Astra
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
90.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.87 meanMedian 2.00 · n=30
Range 0.00–3.00 · SD 0.97 - placement
- 1.20 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.66 - void Deaths
- 3.00
Conflict vs Gemini 3.8 Flash
66.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.07 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 1.08 - placement
- 1.73 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.14 - void Deaths
- 7.00
Conflict vs Opus 5.5
66.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.43 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 0.94 - placement
- 1.47 meanMedian 1.00 · n=30
Range 1.00–3.00 · SD 0.73 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
20.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.40 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.62 - placement
- 2.73 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 1.14 - void Deaths
- 1.00
Challenge telemetry
Gemini 4 Argon
Challenge telemetry
Gemini 4 Argon
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
96.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.27 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.52 - placement
- 1.10 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.55 - void Deaths
- 0.00
Conflict vs Gemini 3.8 Flash
56.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.87 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 0.90 - placement
- 2.13 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.38 - void Deaths
- 2.00
Conflict vs Opus 5.5
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 2.70 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.84 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
16.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.82 - void Deaths
- 0.00
Challenge telemetry
Claude Opus 5.5
Challenge telemetry
Claude Opus 5.5
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
56.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.93 meanMedian 1.00 · n=30
Range 0.00–2.00 · SD 0.74 - placement
- 1.63 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.89 - void Deaths
- 13.00
Conflict vs Gemini 3.8 Flash
76.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.27 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 0.94 - placement
- 1.37 meanMedian 1.00 · n=30
Range 1.00–3.00 · SD 0.72 - void Deaths
- 5.00
Conflict vs Opus 5.5
23.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.63 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.81 - placement
- 2.33 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.03 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
13.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.17 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.38 - placement
- 2.30 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.88 - void Deaths
- 0.00
Challenge telemetry
MiniMax M3.1 Flash
Challenge telemetry
MiniMax M3.1 Flash
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
80.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 1.30 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.70 - void Deaths
- 6.00
Conflict vs Gemini 3.8 Flash
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.23 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.57 - placement
- 2.33 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.80 - void Deaths
- 16.00
Conflict vs Opus 5.5
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.20 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.55 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
23.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 1.77 meanMedian 2.00 · n=30
Range 1.00–2.00 · SD 0.43 - void Deaths
- 2.00
Challenge telemetry
Claude Sonnet 5.5
Challenge telemetry
Claude Sonnet 5.5
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
83.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.43 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.68 - placement
- 1.30 meanMedian 1.00 · n=30
Range 1.00–3.00 · SD 0.70 - void Deaths
- 5.00
Conflict vs Gemini 3.8 Flash
76.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.53 meanMedian 1.50 · n=30
Range 0.00–3.00 · SD 1.01 - placement
- 1.43 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.90 - void Deaths
- 3.00
Conflict vs Opus 5.5
20.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.37 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.67 - placement
- 2.50 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.11 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.37 - placement
- 2.70 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.92 - void Deaths
- 0.00
Challenge telemetry
Claude Fable 5.1
Challenge telemetry
Claude Fable 5.1
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
86.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.70 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.88 - placement
- 1.27 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.74 - void Deaths
- 3.00
Conflict vs Gemini 3.8 Flash
53.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 1.00 meanMedian 1.00 · n=30
Range 0.00–3.00 · SD 0.98 - placement
- 2.03 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.30 - void Deaths
- 2.00
Conflict vs Opus 5.5
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.10 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.31 - placement
- 2.60 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.77 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.63 - void Deaths
- 0.00
Challenge telemetry
Muse Spark Open
Challenge telemetry
Muse Spark Open
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
83.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 1.43 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.04 - void Deaths
- 4.00
Conflict vs Gemini 3.8 Flash
0.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.87 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.90 - void Deaths
- 9.00
Conflict vs Opus 5.5
16.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 2.20 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.85 - void Deaths
- 4.00
Conflict vs GPT-6.1 Sol
13.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 1.97 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.49 - void Deaths
- 1.00
Challenge telemetry
Gemini 3.8 Flash
Challenge telemetry
Gemini 3.8 Flash
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
83.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.17 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.38 - placement
- 1.43 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.04 - void Deaths
- 1.00
Conflict vs Gemini 3.8 Flash
16.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.30 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.65 - placement
- 2.67 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 1.09 - void Deaths
- 2.00
Conflict vs Opus 5.5
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.63 - void Deaths
- 2.00
Conflict vs GPT-6.1 Sol
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.03 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.56 - void Deaths
- 0.00
Challenge telemetry
Gemma 4 31B
Challenge telemetry
Gemma 4 31B
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
26.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.50 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.20 - void Deaths
- 20.00
Conflict vs Gemini 3.8 Flash
13.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.23 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.68 - placement
- 2.23 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.73 - void Deaths
- 17.00
Conflict vs Opus 5.5
3.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.20 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.55 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
20.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.13 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.43 - placement
- 2.20 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.92 - void Deaths
- 2.00
Challenge telemetry
Grok 4.7
Challenge telemetry
Grok 4.7
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
63.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.40 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.56 - placement
- 1.83 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.23 - void Deaths
- 7.00
Conflict vs Gemini 3.8 Flash
40.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.83 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 1.09 - placement
- 2.17 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.21 - void Deaths
- 0.00
Conflict vs Opus 5.5
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.20 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.48 - placement
- 2.50 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.90 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 2.43 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.82 - void Deaths
- 2.00
Challenge telemetry
GLM 5.3
Challenge telemetry
GLM 5.3
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
60.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 1.70 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.99 - void Deaths
- 11.00
Conflict vs Gemini 3.8 Flash
23.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.10 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.40 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.94 - void Deaths
- 14.00
Conflict vs Opus 5.5
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.07 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.25 - placement
- 2.03 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.49 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 1.97 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.41 - void Deaths
- 0.00
Challenge telemetry
Nemotron 3.5 Super VL
Challenge telemetry
Nemotron 3.5 Super VL
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
43.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 2.23 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.25 - void Deaths
- 17.00
Conflict vs Gemini 3.8 Flash
6.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.37 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.89 - void Deaths
- 21.00
Conflict vs Opus 5.5
13.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 1.97 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.49 - void Deaths
- 2.00
Conflict vs GPT-6.1 Sol
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 1.97 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.41 - void Deaths
- 2.00
Challenge telemetry
DeepSeek V4.1 Flash
Challenge telemetry
DeepSeek V4.1 Flash
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
70.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.50 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.68 - placement
- 1.67 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 1.12 - void Deaths
- 8.00
Conflict vs Gemini 3.8 Flash
20.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.50 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.82 - placement
- 2.60 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 1.16 - void Deaths
- 6.00
Conflict vs Opus 5.5
13.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.33 meanMedian 0.00 · n=30
Range 0.00–3.00 · SD 0.84 - placement
- 2.37 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.93 - void Deaths
- 1.00
Conflict vs GPT-6.1 Sol
3.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.43 - void Deaths
- 0.00
Challenge telemetry
GPT-6 Luna
Challenge telemetry
GPT-6 Luna
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
73.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.23 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.43 - placement
- 1.50 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.97 - void Deaths
- 6.00
Conflict vs Gemini 3.8 Flash
16.67 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.27 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.45 - placement
- 3.00 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 1.14 - void Deaths
- 4.00
Conflict vs Opus 5.5
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.07 meanMedian 2.00 · n=30
Range 1.00–3.00 · SD 0.52 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
3.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.03 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.41 - void Deaths
- 2.00
Challenge telemetry
Muse Spark 1.3
Challenge telemetry
Muse Spark 1.3
Section results, sample counts, and the extra metrics recorded by each challenge.
Conflict vs Gemma 4
83.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.23 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.50 - placement
- 1.30 meanMedian 1.00 · n=30
Range 1.00–4.00 · SD 0.75 - void Deaths
- 3.00
Conflict vs Gemini 3.8 Flash
10.00 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.23 meanMedian 0.00 · n=30
Range 0.00–2.00 · SD 0.50 - placement
- 2.73 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.98 - void Deaths
- 4.00
Conflict vs Opus 5.5
3.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.00 meanMedian 0.00 · n=30
Range 0.00–0.00 · SD 0.00 - placement
- 2.67 meanMedian 3.00 · n=30
Range 1.00–4.00 · SD 0.80 - void Deaths
- 0.00
Conflict vs GPT-6.1 Sol
3.33 / 100 · 30 scored runs · 30 planned slots · 0 awaiting judgment
- kills
- 0.03 meanMedian 0.00 · n=30
Range 0.00–1.00 · SD 0.18 - placement
- 2.13 meanMedian 2.00 · n=30
Range 1.00–4.00 · SD 0.51 - void Deaths
- 0.00